{ "metadata": { "total_parameters": 32207337984, "total_size": 32632372656 }, "weight_map": { "model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.10.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.10.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.10.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.10.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.10.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.11.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.11.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.11.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.11.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.11.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.12.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.12.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.12.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.12.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.12.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.13.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.13.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.13.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.13.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.13.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.14.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.14.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.14.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.14.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.14.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.15.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.15.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.15.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.15.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.15.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.16.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.16.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.16.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.16.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.16.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.17.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.17.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.17.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.17.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.17.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.18.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.18.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.18.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.18.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.18.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.19.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.19.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.19.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.19.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.19.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.20.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.20.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.20.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.20.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.20.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.21.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.21.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.21.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.21.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.21.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.22.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.22.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.22.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.22.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.22.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.23.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.23.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.23.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.23.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.23.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.24.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.24.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.24.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.24.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.24.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.25.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.25.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.25.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.25.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.25.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.26.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.26.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.26.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.26.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.26.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.27.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.27.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.27.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.27.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.27.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.28.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.28.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.28.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.28.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.28.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.29.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.29.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.29.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.29.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.29.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.30.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.30.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.30.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.30.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.30.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.31.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.31.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.31.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.31.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.31.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.32.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.32.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.32.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.32.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.32.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.33.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.33.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.33.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.33.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.33.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.34.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.34.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.34.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.34.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.34.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.35.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.35.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.35.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.35.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.35.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.36.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.36.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.36.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.36.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.36.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.37.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.37.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.37.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.37.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.37.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.38.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.38.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.38.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.38.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.38.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.39.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.39.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.39.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.39.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.39.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.4.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.4.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.4.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.4.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.4.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.40.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.40.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.40.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.40.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.40.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.41.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.41.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.41.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.41.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.41.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.42.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.42.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.42.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.42.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.42.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.43.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.43.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.43.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.43.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.43.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.44.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.44.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.44.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.44.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.44.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.45.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.45.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.45.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.45.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.45.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.46.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.46.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.46.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.46.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.46.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.47.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.47.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.47.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.47.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.47.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.48.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.48.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.48.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.48.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.48.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.49.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.49.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.49.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.49.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.49.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.5.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.5.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.5.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.5.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.5.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.50.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.50.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.50.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.50.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.50.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.51.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.51.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.51.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.51.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.51.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.52.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.52.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.52.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.52.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.52.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.53.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.53.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.53.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.53.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.53.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.54.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.54.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.54.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.54.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.54.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.55.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.55.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.55.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.55.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.55.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.56.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.56.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.56.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.56.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.56.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.57.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.57.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.57.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.57.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.57.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.58.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.58.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.58.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.58.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.58.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.59.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.59.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.59.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.59.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.59.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.6.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.6.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.6.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.6.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.6.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.60.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.60.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.60.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.60.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.60.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.61.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.61.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.61.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.61.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.61.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.62.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.62.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.62.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.62.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.62.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.63.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.63.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.63.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.63.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.63.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.64.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.64.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.64.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.64.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.64.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.65.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.65.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.65.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.65.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.65.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.66.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.66.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.66.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.66.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.66.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.67.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.67.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.67.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.67.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.67.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.68.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.68.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.68.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.68.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.68.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.69.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.69.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.69.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.69.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.69.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.7.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.7.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.7.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.7.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.7.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.70.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.70.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.70.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.70.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.70.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.71.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.71.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.71.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.71.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.71.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.8.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.8.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.8.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.8.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.8.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.9.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.9.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.9.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.9.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.9.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.router.layer.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mamba.A_log": "model-00001-of-00007.safetensors", "model.layers.0.mamba.D": "model-00001-of-00007.safetensors", "model.layers.0.mamba.conv1d.bias": "model-00001-of-00007.safetensors", "model.layers.0.mamba.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.0.mamba.dt_bias": "model-00001-of-00007.safetensors", "model.layers.0.mamba.in_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.mamba.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mamba.in_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.mamba.norm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mamba.out_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.mamba.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mamba.out_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.shared_mlp.input_linear.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.shared_mlp.input_linear.weight": "model-00001-of-00007.safetensors", "model.layers.0.shared_mlp.input_linear.weight_scale": "model-00001-of-00007.safetensors", "model.layers.0.shared_mlp.output_linear.input_scale": "model-00001-of-00007.safetensors", "model.layers.0.shared_mlp.output_linear.weight": "model-00001-of-00007.safetensors", "model.layers.0.shared_mlp.output_linear.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.10.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.10.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.10.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.10.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.10.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.11.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.11.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.11.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.11.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.11.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.12.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.12.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.12.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.12.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.12.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.13.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.13.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.13.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.13.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.13.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.14.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.14.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.14.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.14.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.14.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.15.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.15.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.15.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.15.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.15.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.16.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.16.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.16.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.16.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.16.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.17.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.17.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.17.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.17.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.17.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.18.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.18.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.18.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.18.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.18.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.19.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.19.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.19.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.19.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.19.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.20.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.20.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.20.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.20.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.20.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.21.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.21.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.21.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.21.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.21.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.22.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.22.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.22.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.22.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.22.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.23.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.23.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.23.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.23.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.23.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.24.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.24.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.24.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.24.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.24.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.25.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.25.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.25.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.25.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.25.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.26.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.26.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.26.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.26.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.26.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.27.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.27.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.27.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.27.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.27.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.28.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.28.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.28.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.28.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.28.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.29.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.29.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.29.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.29.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.29.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.30.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.30.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.30.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.30.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.30.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.31.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.31.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.31.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.31.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.31.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.32.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.32.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.32.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.32.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.32.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.33.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.33.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.33.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.33.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.33.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.34.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.34.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.34.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.34.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.34.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.35.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.35.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.35.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.35.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.35.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.36.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.36.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.36.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.36.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.36.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.37.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.37.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.37.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.37.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.37.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.38.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.38.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.38.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.38.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.38.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.39.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.39.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.39.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.39.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.39.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.4.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.4.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.4.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.4.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.4.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.40.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.40.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.40.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.40.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.40.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.41.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.41.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.41.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.41.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.41.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.42.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.42.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.42.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.42.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.42.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.43.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.43.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.43.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.43.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.43.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.44.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.44.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.44.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.44.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.44.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.45.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.45.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.45.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.45.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.45.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.46.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.46.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.46.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.46.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.46.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.47.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.47.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.47.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.47.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.47.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.48.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.48.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.48.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.48.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.48.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.49.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.49.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.49.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.49.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.49.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.5.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.5.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.5.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.5.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.5.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.50.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.50.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.50.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.50.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.50.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.51.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.51.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.51.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.51.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.51.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.52.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.52.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.52.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.52.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.52.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.53.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.53.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.53.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.53.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.53.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.54.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.54.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.54.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.54.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.54.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.55.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.55.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.55.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.55.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.55.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.56.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.56.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.56.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.56.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.56.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.57.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.57.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.57.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.57.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.57.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.58.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.58.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.58.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.58.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.58.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.59.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.59.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.59.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.59.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.59.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.6.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.6.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.6.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.6.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.6.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.60.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.60.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.60.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.60.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.60.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.61.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.61.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.61.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.61.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.61.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.62.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.62.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.62.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.62.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.62.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.63.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.63.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.63.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.63.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.63.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.64.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.64.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.64.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.64.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.64.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.65.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.65.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.65.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.65.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.65.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.66.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.66.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.66.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.66.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.66.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.67.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.67.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.67.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.67.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.67.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.68.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.68.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.68.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.68.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.68.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.69.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.69.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.69.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.69.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.69.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.7.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.7.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.7.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.7.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.7.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.70.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.70.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.70.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.70.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.70.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.71.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.71.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.71.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.71.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.71.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.8.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.8.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.8.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.8.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.8.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.9.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.9.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.9.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.9.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.9.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.router.layer.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mamba.A_log": "model-00001-of-00007.safetensors", "model.layers.1.mamba.D": "model-00001-of-00007.safetensors", "model.layers.1.mamba.conv1d.bias": "model-00001-of-00007.safetensors", "model.layers.1.mamba.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.1.mamba.dt_bias": "model-00001-of-00007.safetensors", "model.layers.1.mamba.in_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.mamba.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mamba.in_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.mamba.norm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mamba.out_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.mamba.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mamba.out_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.shared_mlp.input_linear.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.shared_mlp.input_linear.weight": "model-00001-of-00007.safetensors", "model.layers.1.shared_mlp.input_linear.weight_scale": "model-00001-of-00007.safetensors", "model.layers.1.shared_mlp.output_linear.input_scale": "model-00001-of-00007.safetensors", "model.layers.1.shared_mlp.output_linear.weight": "model-00001-of-00007.safetensors", "model.layers.1.shared_mlp.output_linear.weight_scale": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.10.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.10.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.10.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.10.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.10.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.11.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.11.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.11.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.11.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.11.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.12.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.12.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.12.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.12.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.12.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.13.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.13.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.13.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.13.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.13.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.14.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.14.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.14.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.14.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.14.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.15.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.15.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.15.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.15.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.15.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.16.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.16.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.16.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.16.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.16.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.17.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.17.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.17.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.17.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.17.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.18.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.18.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.18.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.18.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.18.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.19.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.19.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.19.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.19.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.19.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.20.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.20.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.20.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.20.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.20.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.21.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.21.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.21.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.21.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.21.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.22.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.22.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.22.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.22.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.22.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.23.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.23.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.23.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.23.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.23.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.24.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.24.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.24.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.24.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.24.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.25.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.25.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.25.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.25.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.25.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.26.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.26.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.26.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.26.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.26.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.27.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.27.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.27.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.27.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.27.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.28.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.28.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.28.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.28.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.28.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.29.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.29.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.29.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.29.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.29.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.30.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.30.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.30.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.30.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.30.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.31.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.31.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.31.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.31.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.31.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.32.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.32.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.32.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.32.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.32.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.33.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.33.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.33.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.33.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.33.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.34.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.34.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.34.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.34.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.34.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.35.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.35.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.35.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.35.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.35.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.36.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.36.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.36.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.36.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.36.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.37.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.37.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.37.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.37.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.37.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.38.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.38.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.38.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.38.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.38.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.39.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.39.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.39.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.39.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.39.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.4.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.4.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.4.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.4.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.4.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.40.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.40.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.40.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.40.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.40.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.41.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.41.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.41.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.41.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.41.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.42.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.42.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.42.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.42.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.42.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.43.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.43.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.43.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.43.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.43.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.44.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.44.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.44.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.44.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.44.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.45.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.45.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.45.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.45.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.45.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.46.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.46.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.46.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.46.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.46.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.47.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.47.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.47.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.47.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.47.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.48.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.48.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.48.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.48.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.48.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.49.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.49.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.49.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.49.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.49.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.5.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.5.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.5.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.5.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.5.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.50.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.50.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.50.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.50.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.50.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.51.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.51.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.51.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.51.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.51.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.52.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.52.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.52.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.52.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.52.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.53.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.53.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.53.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.53.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.53.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.54.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.54.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.54.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.54.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.54.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.55.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.55.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.55.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.55.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.55.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.56.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.56.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.56.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.56.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.56.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.57.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.57.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.57.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.57.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.57.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.58.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.58.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.58.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.58.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.58.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.59.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.59.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.59.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.59.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.59.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.6.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.6.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.6.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.6.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.6.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.60.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.60.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.60.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.60.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.60.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.61.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.61.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.61.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.61.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.61.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.62.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.62.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.62.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.62.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.62.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.63.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.63.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.63.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.63.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.63.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.64.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.64.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.64.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.64.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.64.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.65.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.65.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.65.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.65.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.65.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.66.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.66.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.66.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.66.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.66.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.67.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.67.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.67.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.67.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.67.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.68.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.68.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.68.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.68.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.68.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.69.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.69.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.69.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.69.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.69.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.7.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.7.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.7.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.7.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.7.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.70.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.70.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.70.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.70.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.70.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.71.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.71.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.71.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.71.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.71.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.8.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.8.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.8.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.8.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.8.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.9.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.9.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.9.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.9.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.9.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.block_sparse_moe.router.layer.weight": "model-00002-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.mamba.A_log": "model-00002-of-00007.safetensors", "model.layers.10.mamba.D": "model-00002-of-00007.safetensors", "model.layers.10.mamba.conv1d.bias": "model-00002-of-00007.safetensors", "model.layers.10.mamba.conv1d.weight": "model-00002-of-00007.safetensors", "model.layers.10.mamba.dt_bias": "model-00002-of-00007.safetensors", "model.layers.10.mamba.in_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.mamba.in_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mamba.in_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.mamba.norm.weight": "model-00002-of-00007.safetensors", "model.layers.10.mamba.out_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.mamba.out_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mamba.out_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.shared_mlp.input_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.shared_mlp.input_linear.weight": "model-00002-of-00007.safetensors", "model.layers.10.shared_mlp.input_linear.weight_scale": "model-00002-of-00007.safetensors", "model.layers.10.shared_mlp.output_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.10.shared_mlp.output_linear.weight": "model-00002-of-00007.safetensors", "model.layers.10.shared_mlp.output_linear.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.10.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.10.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.10.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.10.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.10.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.11.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.11.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.11.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.11.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.11.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.12.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.12.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.12.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.12.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.12.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.13.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.13.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.13.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.13.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.13.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.14.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.14.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.14.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.14.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.14.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.15.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.15.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.15.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.15.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.15.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.16.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.16.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.16.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.16.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.16.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.17.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.17.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.17.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.17.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.17.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.18.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.18.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.18.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.18.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.18.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.19.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.19.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.19.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.19.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.19.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.20.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.20.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.20.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.20.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.20.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.21.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.21.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.21.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.21.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.21.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.22.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.22.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.22.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.22.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.22.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.23.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.23.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.23.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.23.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.23.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.24.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.24.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.24.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.24.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.24.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.25.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.25.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.25.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.25.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.25.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.26.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.26.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.26.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.26.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.26.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.27.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.27.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.27.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.27.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.27.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.28.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.28.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.28.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.28.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.28.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.29.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.29.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.29.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.29.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.29.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.30.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.30.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.30.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.30.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.30.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.31.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.31.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.31.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.31.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.31.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.32.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.32.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.32.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.32.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.32.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.33.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.33.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.33.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.33.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.33.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.34.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.34.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.34.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.34.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.34.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.35.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.35.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.35.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.35.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.35.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.36.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.36.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.36.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.36.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.36.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.37.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.37.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.37.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.37.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.37.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.38.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.38.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.38.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.38.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.38.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.39.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.39.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.39.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.39.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.39.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.4.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.4.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.4.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.4.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.4.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.40.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.40.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.40.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.40.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.40.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.41.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.41.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.41.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.41.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.41.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.42.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.42.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.42.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.42.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.42.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.43.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.43.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.43.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.43.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.43.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.44.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.44.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.44.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.44.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.44.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.45.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.45.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.45.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.45.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.45.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.46.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.46.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.46.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.46.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.46.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.47.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.47.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.47.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.47.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.47.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.48.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.48.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.48.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.48.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.48.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.49.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.49.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.49.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.49.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.49.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.5.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.5.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.5.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.5.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.5.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.50.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.50.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.50.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.50.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.50.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.51.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.51.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.51.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.51.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.51.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.52.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.52.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.52.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.52.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.52.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.53.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.53.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.53.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.53.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.53.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.54.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.54.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.54.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.54.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.54.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.55.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.55.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.55.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.55.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.55.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.56.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.56.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.56.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.56.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.56.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.57.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.57.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.57.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.57.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.57.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.58.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.58.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.58.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.58.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.58.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.59.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.59.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.59.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.59.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.59.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.6.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.6.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.6.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.6.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.6.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.60.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.60.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.60.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.60.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.60.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.61.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.61.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.61.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.61.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.61.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.62.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.62.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.62.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.62.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.62.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.63.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.63.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.63.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.63.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.63.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.64.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.64.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.64.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.64.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.64.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.65.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.65.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.65.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.65.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.65.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.66.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.66.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.66.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.66.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.66.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.67.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.67.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.67.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.67.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.67.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.68.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.68.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.68.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.68.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.68.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.69.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.69.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.69.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.69.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.69.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.7.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.7.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.7.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.7.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.7.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.70.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.70.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.70.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.70.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.70.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.71.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.71.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.71.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.71.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.71.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.8.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.8.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.8.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.8.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.8.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.9.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.9.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.9.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.9.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.9.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.11.block_sparse_moe.router.layer.weight": "model-00002-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.mamba.A_log": "model-00003-of-00007.safetensors", "model.layers.11.mamba.D": "model-00003-of-00007.safetensors", "model.layers.11.mamba.conv1d.bias": "model-00003-of-00007.safetensors", "model.layers.11.mamba.conv1d.weight": "model-00003-of-00007.safetensors", "model.layers.11.mamba.dt_bias": "model-00003-of-00007.safetensors", "model.layers.11.mamba.in_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.mamba.in_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mamba.in_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.mamba.norm.weight": "model-00003-of-00007.safetensors", "model.layers.11.mamba.out_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.mamba.out_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mamba.out_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.shared_mlp.input_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.shared_mlp.input_linear.weight": "model-00003-of-00007.safetensors", "model.layers.11.shared_mlp.input_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.11.shared_mlp.output_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.11.shared_mlp.output_linear.weight": "model-00003-of-00007.safetensors", "model.layers.11.shared_mlp.output_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.10.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.10.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.10.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.10.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.10.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.11.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.11.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.11.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.11.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.11.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.12.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.12.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.12.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.12.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.12.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.13.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.13.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.13.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.13.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.13.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.14.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.14.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.14.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.14.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.14.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.15.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.15.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.15.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.15.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.15.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.16.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.16.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.16.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.16.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.16.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.17.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.17.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.17.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.17.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.17.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.18.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.18.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.18.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.18.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.18.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.19.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.19.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.19.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.19.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.19.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.20.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.20.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.20.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.20.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.20.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.21.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.21.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.21.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.21.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.21.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.22.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.22.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.22.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.22.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.22.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.23.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.23.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.23.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.23.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.23.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.24.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.24.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.24.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.24.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.24.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.25.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.25.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.25.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.25.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.25.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.26.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.26.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.26.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.26.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.26.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.27.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.27.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.27.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.27.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.27.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.28.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.28.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.28.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.28.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.28.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.29.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.29.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.29.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.29.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.29.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.30.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.30.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.30.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.30.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.30.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.31.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.31.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.31.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.31.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.31.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.32.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.32.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.32.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.32.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.32.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.33.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.33.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.33.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.33.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.33.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.34.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.34.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.34.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.34.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.34.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.35.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.35.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.35.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.35.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.35.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.36.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.36.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.36.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.36.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.36.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.37.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.37.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.37.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.37.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.37.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.38.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.38.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.38.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.38.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.38.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.39.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.39.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.39.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.39.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.39.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.4.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.4.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.4.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.4.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.4.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.40.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.40.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.40.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.40.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.40.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.41.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.41.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.41.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.41.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.41.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.42.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.42.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.42.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.42.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.42.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.43.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.43.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.43.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.43.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.43.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.44.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.44.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.44.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.44.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.44.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.45.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.45.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.45.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.45.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.45.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.46.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.46.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.46.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.46.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.46.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.47.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.47.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.47.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.47.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.47.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.48.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.48.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.48.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.48.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.48.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.49.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.49.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.49.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.49.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.49.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.5.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.5.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.5.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.5.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.5.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.50.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.50.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.50.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.50.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.50.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.51.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.51.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.51.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.51.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.51.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.52.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.52.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.52.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.52.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.52.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.53.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.53.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.53.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.53.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.53.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.54.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.54.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.54.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.54.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.54.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.55.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.55.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.55.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.55.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.55.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.56.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.56.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.56.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.56.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.56.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.57.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.57.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.57.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.57.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.57.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.58.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.58.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.58.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.58.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.58.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.59.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.59.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.59.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.59.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.59.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.6.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.6.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.6.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.6.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.6.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.60.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.60.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.60.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.60.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.60.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.61.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.61.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.61.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.61.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.61.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.62.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.62.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.62.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.62.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.62.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.63.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.63.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.63.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.63.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.63.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.64.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.64.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.64.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.64.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.64.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.65.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.65.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.65.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.65.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.65.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.66.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.66.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.66.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.66.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.66.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.67.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.67.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.67.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.67.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.67.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.68.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.68.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.68.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.68.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.68.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.69.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.69.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.69.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.69.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.69.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.7.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.7.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.7.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.7.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.7.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.70.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.70.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.70.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.70.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.70.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.71.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.71.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.71.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.71.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.71.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.8.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.8.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.8.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.8.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.8.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.9.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.9.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.9.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.9.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.9.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.router.layer.weight": "model-00003-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.mamba.A_log": "model-00003-of-00007.safetensors", "model.layers.12.mamba.D": "model-00003-of-00007.safetensors", "model.layers.12.mamba.conv1d.bias": "model-00003-of-00007.safetensors", "model.layers.12.mamba.conv1d.weight": "model-00003-of-00007.safetensors", "model.layers.12.mamba.dt_bias": "model-00003-of-00007.safetensors", "model.layers.12.mamba.in_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.mamba.in_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mamba.in_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.mamba.norm.weight": "model-00003-of-00007.safetensors", "model.layers.12.mamba.out_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.mamba.out_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mamba.out_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.shared_mlp.input_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.shared_mlp.input_linear.weight": "model-00003-of-00007.safetensors", "model.layers.12.shared_mlp.input_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.12.shared_mlp.output_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.12.shared_mlp.output_linear.weight": "model-00003-of-00007.safetensors", "model.layers.12.shared_mlp.output_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.10.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.10.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.10.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.10.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.10.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.11.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.11.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.11.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.11.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.11.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.12.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.12.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.12.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.12.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.12.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.13.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.13.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.13.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.13.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.13.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.14.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.14.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.14.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.14.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.14.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.15.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.15.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.15.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.15.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.15.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.16.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.16.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.16.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.16.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.16.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.17.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.17.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.17.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.17.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.17.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.18.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.18.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.18.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.18.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.18.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.19.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.19.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.19.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.19.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.19.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.20.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.20.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.20.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.20.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.20.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.21.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.21.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.21.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.21.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.21.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.22.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.22.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.22.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.22.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.22.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.23.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.23.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.23.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.23.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.23.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.24.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.24.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.24.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.24.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.24.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.25.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.25.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.25.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.25.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.25.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.26.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.26.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.26.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.26.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.26.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.27.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.27.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.27.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.27.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.27.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.28.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.28.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.28.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.28.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.28.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.29.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.29.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.29.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.29.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.29.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.30.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.30.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.30.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.30.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.30.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.31.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.31.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.31.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.31.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.31.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.32.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.32.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.32.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.32.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.32.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.33.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.33.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.33.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.33.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.33.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.34.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.34.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.34.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.34.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.34.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.35.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.35.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.35.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.35.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.35.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.36.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.36.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.36.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.36.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.36.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.37.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.37.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.37.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.37.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.37.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.38.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.38.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.38.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.38.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.38.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.39.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.39.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.39.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.39.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.39.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.4.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.4.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.4.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.4.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.4.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.40.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.40.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.40.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.40.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.40.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.41.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.41.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.41.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.41.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.41.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.42.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.42.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.42.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.42.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.42.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.43.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.43.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.43.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.43.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.43.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.44.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.44.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.44.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.44.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.44.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.45.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.45.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.45.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.45.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.45.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.46.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.46.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.46.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.46.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.46.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.47.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.47.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.47.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.47.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.47.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.48.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.48.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.48.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.48.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.48.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.49.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.49.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.49.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.49.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.49.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.5.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.5.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.5.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.5.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.5.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.50.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.50.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.50.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.50.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.50.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.51.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.51.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.51.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.51.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.51.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.52.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.52.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.52.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.52.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.52.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.53.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.53.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.53.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.53.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.53.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.54.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.54.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.54.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.54.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.54.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.55.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.55.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.55.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.55.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.55.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.56.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.56.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.56.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.56.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.56.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.57.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.57.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.57.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.57.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.57.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.58.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.58.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.58.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.58.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.58.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.59.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.59.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.59.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.59.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.59.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.6.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.6.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.6.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.6.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.6.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.60.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.60.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.60.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.60.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.60.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.61.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.61.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.61.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.61.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.61.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.62.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.62.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.62.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.62.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.62.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.63.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.63.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.63.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.63.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.63.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.64.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.64.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.64.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.64.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.64.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.65.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.65.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.65.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.65.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.65.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.66.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.66.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.66.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.66.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.66.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.67.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.67.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.67.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.67.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.67.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.68.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.68.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.68.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.68.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.68.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.69.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.69.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.69.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.69.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.69.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.7.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.7.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.7.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.7.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.7.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.70.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.70.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.70.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.70.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.70.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.71.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.71.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.71.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.71.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.71.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.8.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.8.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.8.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.8.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.8.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.9.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.9.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.9.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.9.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.9.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.router.layer.weight": "model-00003-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.mamba.A_log": "model-00003-of-00007.safetensors", "model.layers.13.mamba.D": "model-00003-of-00007.safetensors", "model.layers.13.mamba.conv1d.bias": "model-00003-of-00007.safetensors", "model.layers.13.mamba.conv1d.weight": "model-00003-of-00007.safetensors", "model.layers.13.mamba.dt_bias": "model-00003-of-00007.safetensors", "model.layers.13.mamba.in_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.mamba.in_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mamba.in_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.mamba.norm.weight": "model-00003-of-00007.safetensors", "model.layers.13.mamba.out_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.mamba.out_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mamba.out_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.shared_mlp.input_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.shared_mlp.input_linear.weight": "model-00003-of-00007.safetensors", "model.layers.13.shared_mlp.input_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.13.shared_mlp.output_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.13.shared_mlp.output_linear.weight": "model-00003-of-00007.safetensors", "model.layers.13.shared_mlp.output_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.10.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.10.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.10.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.10.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.10.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.11.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.11.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.11.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.11.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.11.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.12.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.12.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.12.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.12.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.12.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.13.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.13.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.13.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.13.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.13.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.14.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.14.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.14.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.14.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.14.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.15.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.15.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.15.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.15.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.15.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.16.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.16.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.16.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.16.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.16.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.17.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.17.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.17.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.17.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.17.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.18.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.18.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.18.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.18.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.18.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.19.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.19.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.19.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.19.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.19.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.20.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.20.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.20.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.20.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.20.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.21.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.21.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.21.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.21.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.21.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.22.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.22.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.22.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.22.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.22.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.23.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.23.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.23.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.23.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.23.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.24.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.24.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.24.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.24.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.24.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.25.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.25.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.25.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.25.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.25.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.26.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.26.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.26.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.26.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.26.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.27.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.27.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.27.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.27.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.27.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.28.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.28.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.28.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.28.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.28.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.29.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.29.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.29.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.29.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.29.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.30.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.30.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.30.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.30.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.30.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.31.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.31.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.31.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.31.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.31.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.32.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.32.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.32.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.32.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.32.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.33.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.33.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.33.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.33.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.33.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.34.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.34.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.34.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.34.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.34.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.35.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.35.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.35.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.35.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.35.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.36.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.36.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.36.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.36.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.36.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.37.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.37.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.37.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.37.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.37.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.38.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.38.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.38.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.38.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.38.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.39.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.39.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.39.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.39.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.39.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.4.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.4.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.4.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.4.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.4.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.40.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.40.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.40.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.40.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.40.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.41.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.41.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.41.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.41.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.41.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.42.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.42.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.42.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.42.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.42.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.43.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.43.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.43.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.43.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.43.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.44.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.44.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.44.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.44.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.44.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.45.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.45.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.45.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.45.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.45.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.46.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.46.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.46.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.46.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.46.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.47.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.47.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.47.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.47.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.47.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.48.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.48.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.48.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.48.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.48.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.49.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.49.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.49.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.49.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.49.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.5.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.5.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.5.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.5.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.5.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.50.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.50.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.50.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.50.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.50.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.51.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.51.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.51.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.51.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.51.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.52.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.52.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.52.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.52.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.52.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.53.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.53.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.53.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.53.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.53.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.54.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.54.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.54.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.54.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.54.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.55.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.55.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.55.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.55.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.55.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.56.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.56.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.56.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.56.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.56.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.57.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.57.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.57.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.57.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.57.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.58.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.58.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.58.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.58.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.58.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.59.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.59.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.59.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.59.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.59.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.6.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.6.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.6.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.6.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.6.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.60.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.60.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.60.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.60.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.60.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.61.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.61.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.61.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.61.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.61.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.62.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.62.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.62.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.62.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.62.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.63.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.63.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.63.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.63.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.63.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.64.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.64.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.64.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.64.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.64.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.65.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.65.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.65.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.65.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.65.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.66.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.66.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.66.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.66.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.66.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.67.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.67.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.67.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.67.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.67.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.68.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.68.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.68.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.68.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.68.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.69.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.69.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.69.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.69.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.69.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.7.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.7.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.7.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.7.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.7.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.70.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.70.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.70.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.70.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.70.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.71.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.71.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.71.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.71.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.71.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.8.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.8.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.8.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.8.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.8.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.9.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.9.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.9.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.9.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.9.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.router.layer.weight": "model-00003-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.mamba.A_log": "model-00003-of-00007.safetensors", "model.layers.14.mamba.D": "model-00003-of-00007.safetensors", "model.layers.14.mamba.conv1d.bias": "model-00003-of-00007.safetensors", "model.layers.14.mamba.conv1d.weight": "model-00003-of-00007.safetensors", "model.layers.14.mamba.dt_bias": "model-00003-of-00007.safetensors", "model.layers.14.mamba.in_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.mamba.in_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.mamba.in_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.mamba.norm.weight": "model-00003-of-00007.safetensors", "model.layers.14.mamba.out_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.mamba.out_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.mamba.out_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.shared_mlp.input_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.shared_mlp.input_linear.weight": "model-00003-of-00007.safetensors", "model.layers.14.shared_mlp.input_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.14.shared_mlp.output_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.14.shared_mlp.output_linear.weight": "model-00003-of-00007.safetensors", "model.layers.14.shared_mlp.output_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.10.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.10.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.10.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.10.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.10.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.11.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.11.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.11.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.11.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.11.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.12.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.12.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.12.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.12.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.12.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.13.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.13.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.13.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.13.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.13.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.14.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.14.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.14.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.14.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.14.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.15.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.15.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.15.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.15.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.15.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.16.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.16.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.16.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.16.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.16.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.17.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.17.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.17.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.17.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.17.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.18.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.18.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.18.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.18.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.18.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.19.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.19.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.19.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.19.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.19.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.20.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.20.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.20.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.20.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.20.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.21.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.21.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.21.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.21.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.21.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.22.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.22.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.22.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.22.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.22.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.23.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.23.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.23.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.23.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.23.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.24.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.24.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.24.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.24.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.24.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.25.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.25.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.25.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.25.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.25.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.26.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.26.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.26.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.26.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.26.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.27.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.27.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.27.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.27.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.27.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.28.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.28.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.28.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.28.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.28.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.29.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.29.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.29.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.29.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.29.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.30.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.30.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.30.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.30.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.30.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.31.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.31.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.31.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.31.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.31.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.32.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.32.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.32.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.32.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.32.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.33.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.33.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.33.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.33.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.33.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.34.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.34.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.34.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.34.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.34.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.35.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.35.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.35.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.35.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.35.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.36.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.36.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.36.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.36.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.36.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.37.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.37.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.37.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.37.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.37.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.38.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.38.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.38.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.38.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.38.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.39.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.39.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.39.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.39.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.39.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.4.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.4.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.4.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.4.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.4.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.40.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.40.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.40.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.40.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.40.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.41.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.41.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.41.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.41.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.41.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.42.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.42.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.42.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.42.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.42.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.43.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.43.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.43.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.43.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.43.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.44.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.44.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.44.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.44.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.44.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.45.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.45.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.45.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.45.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.45.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.46.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.46.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.46.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.46.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.46.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.47.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.47.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.47.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.47.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.47.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.48.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.48.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.48.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.48.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.48.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.49.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.49.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.49.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.49.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.49.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.5.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.5.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.5.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.5.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.5.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.50.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.50.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.50.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.50.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.50.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.51.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.51.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.51.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.51.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.51.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.52.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.52.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.52.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.52.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.52.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.53.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.53.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.53.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.53.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.53.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.54.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.54.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.54.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.54.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.54.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.55.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.55.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.55.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.55.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.55.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.56.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.56.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.56.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.56.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.56.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.57.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.57.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.57.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.57.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.57.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.58.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.58.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.58.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.58.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.58.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.59.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.59.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.59.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.59.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.59.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.6.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.6.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.6.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.6.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.6.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.60.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.60.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.60.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.60.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.60.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.61.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.61.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.61.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.61.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.61.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.62.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.62.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.62.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.62.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.62.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.63.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.63.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.63.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.63.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.63.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.64.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.64.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.64.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.64.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.64.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.65.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.65.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.65.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.65.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.65.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.66.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.66.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.66.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.66.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.66.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.67.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.67.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.67.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.67.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.67.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.68.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.68.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.68.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.68.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.68.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.69.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.69.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.69.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.69.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.69.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.7.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.7.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.7.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.7.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.7.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.70.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.70.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.70.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.70.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.70.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.71.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.71.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.71.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.71.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.71.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.8.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.8.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.8.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.8.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.8.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.9.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.9.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.9.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.9.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.9.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.router.layer.weight": "model-00003-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.k_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.k_proj.output_scale": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.o_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.q_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.v_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.v_proj.output_scale": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.shared_mlp.input_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.shared_mlp.input_linear.weight": "model-00003-of-00007.safetensors", "model.layers.15.shared_mlp.input_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.15.shared_mlp.output_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.15.shared_mlp.output_linear.weight": "model-00003-of-00007.safetensors", "model.layers.15.shared_mlp.output_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.10.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.10.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.10.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.10.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.10.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.11.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.11.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.11.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.11.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.11.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.12.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.12.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.12.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.12.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.12.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.13.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.13.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.13.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.13.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.13.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.14.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.14.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.14.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.14.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.14.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.15.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.15.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.15.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.15.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.15.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.16.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.16.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.16.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.16.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.16.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.17.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.17.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.17.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.17.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.17.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.18.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.18.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.18.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.18.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.18.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.19.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.19.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.19.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.19.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.19.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.20.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.20.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.20.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.20.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.20.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.21.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.21.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.21.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.21.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.21.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.22.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.22.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.22.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.22.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.22.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.23.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.23.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.23.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.23.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.23.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.24.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.24.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.24.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.24.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.24.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.25.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.25.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.25.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.25.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.25.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.26.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.26.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.26.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.26.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.26.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.27.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.27.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.27.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.27.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.27.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.28.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.28.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.28.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.28.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.28.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.29.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.29.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.29.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.29.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.29.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.30.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.30.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.30.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.30.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.30.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.31.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.31.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.31.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.31.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.31.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.32.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.32.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.32.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.32.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.32.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.33.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.33.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.33.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.33.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.33.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.34.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.34.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.34.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.34.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.34.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.35.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.35.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.35.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.35.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.35.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.36.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.36.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.36.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.36.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.36.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.37.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.37.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.37.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.37.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.37.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.38.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.38.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.38.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.38.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.38.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.39.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.39.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.39.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.39.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.39.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.4.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.4.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.4.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.4.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.4.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.40.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.40.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.40.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.40.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.40.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.41.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.41.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.41.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.41.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.41.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.42.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.42.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.42.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.42.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.42.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.43.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.43.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.43.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.43.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.43.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.44.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.44.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.44.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.44.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.44.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.45.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.45.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.45.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.45.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.45.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.46.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.46.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.46.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.46.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.46.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.47.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.47.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.47.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.47.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.47.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.48.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.48.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.48.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.48.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.48.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.49.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.49.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.49.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.49.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.49.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.5.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.5.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.5.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.5.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.5.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.50.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.50.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.50.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.50.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.50.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.51.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.51.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.51.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.51.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.51.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.52.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.52.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.52.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.52.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.52.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.53.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.53.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.53.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.53.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.53.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.54.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.54.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.54.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.54.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.54.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.55.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.55.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.55.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.55.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.55.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.56.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.56.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.56.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.56.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.56.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.57.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.57.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.57.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.57.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.57.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.58.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.58.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.58.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.58.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.58.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.59.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.59.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.59.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.59.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.59.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.6.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.6.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.6.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.6.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.6.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.60.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.60.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.60.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.60.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.60.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.61.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.61.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.61.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.61.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.61.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.62.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.62.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.62.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.62.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.62.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.63.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.63.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.63.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.63.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.63.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.64.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.64.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.64.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.64.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.64.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.65.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.65.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.65.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.65.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.65.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.66.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.66.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.66.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.66.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.66.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.67.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.67.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.67.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.67.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.67.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.68.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.68.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.68.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.68.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.68.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.69.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.69.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.69.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.69.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.69.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.7.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.7.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.7.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.7.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.7.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.70.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.70.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.70.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.70.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.70.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.71.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.71.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.71.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.71.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.71.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.8.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.8.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.8.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.8.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.8.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.9.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.9.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.9.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.9.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.9.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.router.layer.weight": "model-00003-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.mamba.A_log": "model-00003-of-00007.safetensors", "model.layers.16.mamba.D": "model-00003-of-00007.safetensors", "model.layers.16.mamba.conv1d.bias": "model-00003-of-00007.safetensors", "model.layers.16.mamba.conv1d.weight": "model-00003-of-00007.safetensors", "model.layers.16.mamba.dt_bias": "model-00003-of-00007.safetensors", "model.layers.16.mamba.in_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.mamba.in_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mamba.in_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.mamba.norm.weight": "model-00003-of-00007.safetensors", "model.layers.16.mamba.out_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.mamba.out_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mamba.out_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.shared_mlp.input_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.shared_mlp.input_linear.weight": "model-00003-of-00007.safetensors", "model.layers.16.shared_mlp.input_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.16.shared_mlp.output_linear.input_scale": "model-00003-of-00007.safetensors", "model.layers.16.shared_mlp.output_linear.weight": "model-00003-of-00007.safetensors", "model.layers.16.shared_mlp.output_linear.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.10.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.10.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.10.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.10.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.10.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.11.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.11.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.11.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.11.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.11.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.12.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.12.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.12.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.12.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.12.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.13.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.13.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.13.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.13.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.13.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.14.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.14.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.14.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.14.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.14.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.15.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.15.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.15.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.15.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.15.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.16.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.16.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.16.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.16.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.16.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.17.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.17.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.17.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.17.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.17.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.18.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.18.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.18.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.18.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.18.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.19.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.19.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.19.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.19.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.19.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.20.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.20.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.20.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.20.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.20.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.21.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.21.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.21.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.21.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.21.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.22.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.22.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.22.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.22.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.22.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.23.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.23.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.23.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.23.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.23.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.24.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.24.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.24.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.24.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.24.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.25.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.25.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.25.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.25.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.25.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.26.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.26.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.26.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.26.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.26.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.27.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.27.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.27.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.27.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.27.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.28.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.28.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.28.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.28.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.28.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.29.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.29.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.29.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.29.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.29.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.30.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.30.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.30.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.30.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.30.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.31.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.31.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.31.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.31.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.31.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.32.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.32.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.32.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.32.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.32.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.33.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.33.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.33.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.33.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.33.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.34.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.34.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.34.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.34.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.34.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.35.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.35.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.35.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.35.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.35.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.36.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.36.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.36.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.36.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.36.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.37.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.37.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.37.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.37.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.37.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.38.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.38.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.38.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.38.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.38.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.39.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.39.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.39.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.39.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.39.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.4.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.4.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.4.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.4.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.4.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.40.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.40.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.40.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.40.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.40.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.41.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.41.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.41.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.41.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.41.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.42.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.42.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.42.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.42.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.42.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.43.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.43.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.43.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.43.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.43.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.44.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.44.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.44.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.44.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.44.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.45.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.45.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.45.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.45.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.45.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.46.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.46.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.46.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.46.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.46.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.47.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.47.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.47.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.47.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.47.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.48.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.48.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.48.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.48.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.48.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.49.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.49.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.49.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.49.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.49.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.5.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.5.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.5.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.5.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.5.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.50.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.50.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.50.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.50.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.50.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.51.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.51.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.51.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.51.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.51.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.52.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.52.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.52.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.52.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.52.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.53.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.53.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.53.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.53.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.53.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.54.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.54.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.54.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.54.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.54.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.55.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.55.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.55.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.55.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.55.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.56.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.56.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.56.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.56.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.56.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.57.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.57.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.57.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.57.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.57.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.58.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.58.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.58.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.58.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.58.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.59.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.59.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.59.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.59.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.59.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.6.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.6.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.6.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.6.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.6.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.60.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.60.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.60.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.60.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.60.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.61.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.61.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.61.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.61.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.61.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.62.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.62.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.62.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.62.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.62.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.63.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.63.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.63.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.63.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.63.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.64.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.64.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.64.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.64.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.64.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.65.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.65.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.65.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.65.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.65.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.66.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.66.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.66.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.66.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.66.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.67.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.67.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.67.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.67.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.67.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.68.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.68.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.68.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.68.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.68.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.69.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.69.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.69.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.69.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.69.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.7.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.7.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.7.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.7.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.7.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.70.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.70.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.70.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.70.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.70.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.71.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.71.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.71.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.71.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.71.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.8.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.8.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.8.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.8.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.8.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.9.down_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.9.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.9.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.9.up_proj.input_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.9.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.router.layer.weight": "model-00003-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.mamba.A_log": "model-00004-of-00007.safetensors", "model.layers.17.mamba.D": "model-00004-of-00007.safetensors", "model.layers.17.mamba.conv1d.bias": "model-00004-of-00007.safetensors", "model.layers.17.mamba.conv1d.weight": "model-00004-of-00007.safetensors", "model.layers.17.mamba.dt_bias": "model-00004-of-00007.safetensors", "model.layers.17.mamba.in_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.17.mamba.in_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mamba.in_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.17.mamba.norm.weight": "model-00004-of-00007.safetensors", "model.layers.17.mamba.out_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.17.mamba.out_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mamba.out_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.shared_mlp.input_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.17.shared_mlp.input_linear.weight": "model-00004-of-00007.safetensors", "model.layers.17.shared_mlp.input_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.17.shared_mlp.output_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.17.shared_mlp.output_linear.weight": "model-00004-of-00007.safetensors", "model.layers.17.shared_mlp.output_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.10.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.10.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.10.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.10.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.10.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.11.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.11.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.11.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.11.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.11.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.12.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.12.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.12.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.12.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.12.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.13.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.13.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.13.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.13.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.13.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.14.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.14.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.14.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.14.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.14.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.15.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.15.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.15.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.15.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.15.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.16.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.16.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.16.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.16.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.16.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.17.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.17.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.17.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.17.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.17.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.18.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.18.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.18.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.18.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.18.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.19.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.19.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.19.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.19.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.19.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.20.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.20.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.20.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.20.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.20.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.21.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.21.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.21.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.21.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.21.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.22.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.22.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.22.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.22.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.22.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.23.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.23.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.23.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.23.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.23.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.24.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.24.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.24.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.24.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.24.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.25.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.25.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.25.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.25.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.25.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.26.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.26.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.26.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.26.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.26.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.27.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.27.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.27.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.27.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.27.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.28.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.28.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.28.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.28.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.28.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.29.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.29.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.29.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.29.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.29.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.30.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.30.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.30.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.30.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.30.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.31.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.31.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.31.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.31.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.31.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.32.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.32.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.32.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.32.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.32.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.33.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.33.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.33.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.33.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.33.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.34.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.34.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.34.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.34.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.34.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.35.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.35.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.35.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.35.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.35.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.36.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.36.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.36.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.36.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.36.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.37.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.37.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.37.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.37.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.37.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.38.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.38.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.38.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.38.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.38.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.39.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.39.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.39.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.39.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.39.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.4.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.4.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.4.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.4.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.4.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.40.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.40.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.40.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.40.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.40.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.41.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.41.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.41.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.41.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.41.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.42.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.42.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.42.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.42.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.42.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.43.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.43.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.43.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.43.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.43.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.44.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.44.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.44.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.44.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.44.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.45.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.45.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.45.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.45.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.45.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.46.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.46.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.46.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.46.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.46.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.47.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.47.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.47.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.47.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.47.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.48.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.48.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.48.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.48.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.48.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.49.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.49.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.49.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.49.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.49.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.5.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.5.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.5.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.5.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.5.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.50.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.50.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.50.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.50.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.50.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.51.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.51.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.51.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.51.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.51.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.52.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.52.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.52.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.52.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.52.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.53.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.53.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.53.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.53.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.53.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.54.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.54.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.54.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.54.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.54.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.55.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.55.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.55.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.55.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.55.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.56.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.56.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.56.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.56.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.56.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.57.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.57.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.57.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.57.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.57.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.58.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.58.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.58.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.58.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.58.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.59.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.59.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.59.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.59.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.59.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.6.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.6.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.6.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.6.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.6.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.60.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.60.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.60.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.60.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.60.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.61.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.61.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.61.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.61.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.61.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.62.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.62.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.62.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.62.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.62.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.63.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.63.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.63.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.63.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.63.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.64.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.64.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.64.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.64.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.64.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.65.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.65.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.65.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.65.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.65.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.66.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.66.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.66.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.66.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.66.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.67.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.67.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.67.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.67.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.67.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.68.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.68.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.68.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.68.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.68.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.69.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.69.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.69.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.69.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.69.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.7.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.7.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.7.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.7.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.7.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.70.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.70.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.70.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.70.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.70.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.71.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.71.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.71.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.71.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.71.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.8.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.8.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.8.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.8.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.8.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.9.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.9.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.9.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.9.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.9.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.router.layer.weight": "model-00004-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.18.mamba.A_log": "model-00004-of-00007.safetensors", "model.layers.18.mamba.D": "model-00004-of-00007.safetensors", "model.layers.18.mamba.conv1d.bias": "model-00004-of-00007.safetensors", "model.layers.18.mamba.conv1d.weight": "model-00004-of-00007.safetensors", "model.layers.18.mamba.dt_bias": "model-00004-of-00007.safetensors", "model.layers.18.mamba.in_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.mamba.in_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.mamba.in_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.mamba.norm.weight": "model-00004-of-00007.safetensors", "model.layers.18.mamba.out_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.mamba.out_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.mamba.out_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.18.shared_mlp.input_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.shared_mlp.input_linear.weight": "model-00004-of-00007.safetensors", "model.layers.18.shared_mlp.input_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.18.shared_mlp.output_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.18.shared_mlp.output_linear.weight": "model-00004-of-00007.safetensors", "model.layers.18.shared_mlp.output_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.10.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.10.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.10.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.10.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.10.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.11.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.11.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.11.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.11.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.11.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.12.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.12.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.12.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.12.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.12.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.13.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.13.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.13.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.13.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.13.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.14.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.14.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.14.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.14.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.14.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.15.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.15.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.15.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.15.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.15.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.16.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.16.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.16.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.16.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.16.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.17.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.17.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.17.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.17.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.17.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.18.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.18.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.18.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.18.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.18.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.19.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.19.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.19.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.19.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.19.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.20.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.20.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.20.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.20.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.20.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.21.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.21.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.21.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.21.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.21.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.22.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.22.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.22.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.22.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.22.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.23.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.23.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.23.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.23.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.23.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.24.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.24.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.24.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.24.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.24.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.25.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.25.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.25.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.25.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.25.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.26.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.26.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.26.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.26.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.26.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.27.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.27.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.27.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.27.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.27.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.28.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.28.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.28.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.28.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.28.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.29.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.29.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.29.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.29.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.29.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.30.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.30.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.30.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.30.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.30.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.31.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.31.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.31.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.31.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.31.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.32.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.32.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.32.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.32.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.32.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.33.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.33.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.33.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.33.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.33.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.34.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.34.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.34.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.34.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.34.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.35.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.35.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.35.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.35.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.35.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.36.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.36.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.36.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.36.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.36.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.37.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.37.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.37.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.37.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.37.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.38.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.38.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.38.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.38.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.38.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.39.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.39.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.39.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.39.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.39.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.4.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.4.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.4.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.4.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.4.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.40.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.40.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.40.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.40.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.40.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.41.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.41.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.41.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.41.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.41.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.42.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.42.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.42.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.42.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.42.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.43.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.43.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.43.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.43.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.43.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.44.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.44.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.44.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.44.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.44.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.45.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.45.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.45.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.45.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.45.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.46.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.46.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.46.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.46.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.46.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.47.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.47.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.47.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.47.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.47.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.48.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.48.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.48.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.48.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.48.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.49.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.49.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.49.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.49.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.49.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.5.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.5.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.5.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.5.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.5.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.50.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.50.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.50.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.50.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.50.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.51.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.51.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.51.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.51.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.51.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.52.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.52.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.52.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.52.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.52.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.53.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.53.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.53.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.53.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.53.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.54.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.54.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.54.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.54.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.54.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.55.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.55.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.55.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.55.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.55.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.56.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.56.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.56.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.56.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.56.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.57.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.57.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.57.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.57.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.57.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.58.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.58.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.58.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.58.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.58.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.59.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.59.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.59.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.59.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.59.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.6.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.6.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.6.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.6.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.6.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.60.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.60.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.60.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.60.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.60.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.61.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.61.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.61.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.61.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.61.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.62.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.62.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.62.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.62.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.62.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.63.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.63.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.63.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.63.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.63.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.64.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.64.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.64.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.64.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.64.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.65.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.65.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.65.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.65.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.65.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.66.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.66.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.66.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.66.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.66.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.67.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.67.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.67.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.67.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.67.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.68.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.68.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.68.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.68.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.68.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.69.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.69.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.69.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.69.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.69.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.7.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.7.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.7.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.7.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.7.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.70.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.70.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.70.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.70.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.70.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.71.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.71.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.71.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.71.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.71.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.8.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.8.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.8.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.8.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.8.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.9.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.9.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.9.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.9.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.9.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.router.layer.weight": "model-00004-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.19.mamba.A_log": "model-00004-of-00007.safetensors", "model.layers.19.mamba.D": "model-00004-of-00007.safetensors", "model.layers.19.mamba.conv1d.bias": "model-00004-of-00007.safetensors", "model.layers.19.mamba.conv1d.weight": "model-00004-of-00007.safetensors", "model.layers.19.mamba.dt_bias": "model-00004-of-00007.safetensors", "model.layers.19.mamba.in_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.mamba.in_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.mamba.in_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.mamba.norm.weight": "model-00004-of-00007.safetensors", "model.layers.19.mamba.out_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.mamba.out_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.mamba.out_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.19.shared_mlp.input_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.shared_mlp.input_linear.weight": "model-00004-of-00007.safetensors", "model.layers.19.shared_mlp.input_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.19.shared_mlp.output_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.19.shared_mlp.output_linear.weight": "model-00004-of-00007.safetensors", "model.layers.19.shared_mlp.output_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.10.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.10.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.10.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.10.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.10.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.11.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.11.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.11.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.11.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.11.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.12.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.12.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.12.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.12.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.12.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.13.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.13.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.13.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.13.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.13.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.14.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.14.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.14.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.14.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.14.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.15.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.15.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.15.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.15.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.15.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.16.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.16.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.16.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.16.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.16.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.17.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.17.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.17.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.17.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.17.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.18.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.18.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.18.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.18.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.18.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.19.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.19.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.19.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.19.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.19.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.20.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.20.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.20.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.20.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.20.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.21.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.21.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.21.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.21.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.21.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.22.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.22.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.22.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.22.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.22.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.23.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.23.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.23.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.23.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.23.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.24.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.24.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.24.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.24.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.24.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.25.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.25.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.25.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.25.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.25.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.26.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.26.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.26.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.26.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.26.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.27.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.27.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.27.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.27.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.27.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.28.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.28.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.28.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.28.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.28.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.29.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.29.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.29.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.29.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.29.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.30.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.30.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.30.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.30.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.30.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.31.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.31.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.31.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.31.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.31.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.32.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.32.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.32.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.32.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.32.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.33.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.33.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.33.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.33.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.33.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.34.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.34.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.34.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.34.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.34.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.35.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.35.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.35.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.35.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.35.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.36.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.36.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.36.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.36.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.36.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.37.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.37.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.37.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.37.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.37.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.38.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.38.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.38.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.38.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.38.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.39.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.39.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.39.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.39.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.39.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.4.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.4.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.4.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.4.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.4.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.40.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.40.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.40.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.40.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.40.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.41.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.41.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.41.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.41.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.41.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.42.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.42.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.42.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.42.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.42.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.43.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.43.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.43.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.43.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.43.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.44.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.44.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.44.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.44.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.44.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.45.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.45.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.45.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.45.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.45.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.46.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.46.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.46.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.46.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.46.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.47.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.47.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.47.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.47.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.47.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.48.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.48.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.48.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.48.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.48.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.49.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.49.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.49.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.49.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.49.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.5.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.5.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.5.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.5.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.5.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.50.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.50.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.50.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.50.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.50.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.51.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.51.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.51.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.51.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.51.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.52.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.52.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.52.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.52.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.52.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.53.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.53.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.53.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.53.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.53.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.54.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.54.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.54.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.54.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.54.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.55.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.55.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.55.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.55.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.55.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.56.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.56.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.56.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.56.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.56.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.57.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.57.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.57.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.57.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.57.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.58.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.58.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.58.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.58.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.58.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.59.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.59.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.59.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.59.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.59.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.6.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.6.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.6.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.6.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.6.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.60.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.60.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.60.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.60.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.60.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.61.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.61.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.61.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.61.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.61.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.62.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.62.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.62.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.62.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.62.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.63.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.63.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.63.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.63.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.63.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.64.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.64.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.64.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.64.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.64.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.65.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.65.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.65.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.65.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.65.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.66.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.66.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.66.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.66.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.66.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.67.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.67.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.67.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.67.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.67.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.68.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.68.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.68.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.68.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.68.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.69.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.69.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.69.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.69.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.69.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.7.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.7.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.7.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.7.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.7.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.70.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.70.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.70.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.70.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.70.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.71.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.71.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.71.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.71.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.71.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.8.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.8.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.8.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.8.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.8.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.9.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.9.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.9.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.9.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.9.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.router.layer.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.mamba.A_log": "model-00001-of-00007.safetensors", "model.layers.2.mamba.D": "model-00001-of-00007.safetensors", "model.layers.2.mamba.conv1d.bias": "model-00001-of-00007.safetensors", "model.layers.2.mamba.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.2.mamba.dt_bias": "model-00001-of-00007.safetensors", "model.layers.2.mamba.in_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.mamba.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mamba.in_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.mamba.norm.weight": "model-00001-of-00007.safetensors", "model.layers.2.mamba.out_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.mamba.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mamba.out_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.shared_mlp.input_linear.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.shared_mlp.input_linear.weight": "model-00001-of-00007.safetensors", "model.layers.2.shared_mlp.input_linear.weight_scale": "model-00001-of-00007.safetensors", "model.layers.2.shared_mlp.output_linear.input_scale": "model-00001-of-00007.safetensors", "model.layers.2.shared_mlp.output_linear.weight": "model-00001-of-00007.safetensors", "model.layers.2.shared_mlp.output_linear.weight_scale": "model-00001-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.10.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.10.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.10.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.10.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.10.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.11.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.11.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.11.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.11.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.11.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.12.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.12.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.12.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.12.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.12.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.13.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.13.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.13.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.13.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.13.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.14.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.14.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.14.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.14.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.14.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.15.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.15.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.15.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.15.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.15.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.16.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.16.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.16.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.16.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.16.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.17.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.17.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.17.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.17.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.17.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.18.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.18.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.18.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.18.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.18.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.19.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.19.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.19.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.19.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.19.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.20.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.20.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.20.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.20.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.20.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.21.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.21.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.21.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.21.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.21.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.22.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.22.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.22.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.22.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.22.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.23.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.23.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.23.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.23.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.23.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.24.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.24.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.24.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.24.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.24.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.25.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.25.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.25.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.25.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.25.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.26.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.26.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.26.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.26.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.26.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.27.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.27.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.27.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.27.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.27.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.28.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.28.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.28.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.28.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.28.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.29.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.29.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.29.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.29.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.29.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.30.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.30.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.30.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.30.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.30.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.31.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.31.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.31.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.31.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.31.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.32.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.32.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.32.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.32.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.32.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.33.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.33.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.33.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.33.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.33.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.34.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.34.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.34.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.34.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.34.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.35.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.35.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.35.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.35.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.35.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.36.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.36.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.36.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.36.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.36.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.37.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.37.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.37.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.37.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.37.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.38.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.38.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.38.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.38.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.38.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.39.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.39.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.39.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.39.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.39.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.4.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.4.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.4.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.4.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.4.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.40.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.40.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.40.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.40.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.40.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.41.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.41.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.41.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.41.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.41.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.42.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.42.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.42.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.42.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.42.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.43.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.43.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.43.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.43.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.43.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.44.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.44.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.44.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.44.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.44.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.45.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.45.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.45.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.45.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.45.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.46.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.46.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.46.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.46.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.46.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.47.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.47.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.47.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.47.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.47.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.48.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.48.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.48.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.48.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.48.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.49.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.49.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.49.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.49.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.49.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.5.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.5.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.5.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.5.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.5.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.50.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.50.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.50.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.50.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.50.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.51.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.51.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.51.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.51.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.51.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.52.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.52.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.52.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.52.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.52.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.53.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.53.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.53.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.53.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.53.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.54.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.54.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.54.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.54.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.54.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.55.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.55.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.55.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.55.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.55.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.56.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.56.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.56.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.56.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.56.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.57.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.57.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.57.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.57.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.57.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.58.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.58.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.58.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.58.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.58.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.59.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.59.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.59.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.59.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.59.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.6.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.6.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.6.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.6.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.6.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.60.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.60.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.60.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.60.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.60.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.61.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.61.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.61.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.61.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.61.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.62.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.62.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.62.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.62.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.62.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.63.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.63.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.63.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.63.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.63.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.64.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.64.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.64.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.64.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.64.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.65.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.65.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.65.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.65.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.65.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.66.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.66.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.66.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.66.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.66.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.67.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.67.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.67.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.67.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.67.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.68.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.68.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.68.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.68.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.68.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.69.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.69.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.69.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.69.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.69.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.7.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.7.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.7.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.7.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.7.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.70.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.70.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.70.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.70.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.70.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.71.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.71.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.71.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.71.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.71.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.8.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.8.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.8.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.8.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.8.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.9.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.9.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.9.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.9.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.9.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.router.layer.weight": "model-00004-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.20.mamba.A_log": "model-00004-of-00007.safetensors", "model.layers.20.mamba.D": "model-00004-of-00007.safetensors", "model.layers.20.mamba.conv1d.bias": "model-00004-of-00007.safetensors", "model.layers.20.mamba.conv1d.weight": "model-00004-of-00007.safetensors", "model.layers.20.mamba.dt_bias": "model-00004-of-00007.safetensors", "model.layers.20.mamba.in_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.mamba.in_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.mamba.in_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.mamba.norm.weight": "model-00004-of-00007.safetensors", "model.layers.20.mamba.out_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.mamba.out_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.mamba.out_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.20.shared_mlp.input_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.shared_mlp.input_linear.weight": "model-00004-of-00007.safetensors", "model.layers.20.shared_mlp.input_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.20.shared_mlp.output_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.20.shared_mlp.output_linear.weight": "model-00004-of-00007.safetensors", "model.layers.20.shared_mlp.output_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.10.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.10.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.10.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.10.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.10.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.11.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.11.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.11.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.11.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.11.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.12.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.12.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.12.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.12.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.12.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.13.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.13.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.13.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.13.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.13.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.14.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.14.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.14.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.14.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.14.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.15.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.15.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.15.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.15.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.15.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.16.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.16.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.16.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.16.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.16.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.17.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.17.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.17.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.17.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.17.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.18.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.18.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.18.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.18.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.18.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.19.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.19.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.19.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.19.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.19.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.20.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.20.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.20.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.20.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.20.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.21.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.21.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.21.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.21.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.21.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.22.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.22.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.22.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.22.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.22.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.23.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.23.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.23.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.23.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.23.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.24.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.24.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.24.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.24.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.24.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.25.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.25.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.25.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.25.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.25.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.26.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.26.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.26.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.26.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.26.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.27.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.27.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.27.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.27.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.27.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.28.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.28.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.28.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.28.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.28.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.29.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.29.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.29.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.29.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.29.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.30.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.30.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.30.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.30.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.30.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.31.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.31.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.31.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.31.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.31.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.32.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.32.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.32.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.32.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.32.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.33.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.33.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.33.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.33.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.33.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.34.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.34.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.34.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.34.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.34.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.35.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.35.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.35.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.35.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.35.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.36.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.36.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.36.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.36.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.36.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.37.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.37.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.37.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.37.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.37.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.38.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.38.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.38.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.38.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.38.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.39.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.39.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.39.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.39.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.39.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.4.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.4.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.4.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.4.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.4.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.40.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.40.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.40.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.40.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.40.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.41.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.41.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.41.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.41.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.41.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.42.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.42.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.42.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.42.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.42.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.43.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.43.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.43.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.43.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.43.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.44.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.44.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.44.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.44.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.44.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.45.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.45.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.45.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.45.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.45.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.46.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.46.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.46.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.46.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.46.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.47.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.47.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.47.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.47.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.47.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.48.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.48.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.48.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.48.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.48.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.49.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.49.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.49.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.49.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.49.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.5.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.5.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.5.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.5.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.5.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.50.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.50.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.50.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.50.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.50.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.51.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.51.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.51.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.51.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.51.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.52.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.52.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.52.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.52.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.52.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.53.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.53.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.53.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.53.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.53.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.54.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.54.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.54.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.54.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.54.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.55.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.55.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.55.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.55.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.55.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.56.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.56.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.56.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.56.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.56.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.57.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.57.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.57.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.57.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.57.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.58.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.58.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.58.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.58.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.58.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.59.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.59.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.59.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.59.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.59.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.6.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.6.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.6.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.6.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.6.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.60.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.60.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.60.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.60.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.60.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.61.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.61.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.61.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.61.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.61.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.62.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.62.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.62.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.62.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.62.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.63.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.63.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.63.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.63.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.63.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.64.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.64.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.64.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.64.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.64.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.65.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.65.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.65.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.65.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.65.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.66.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.66.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.66.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.66.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.66.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.67.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.67.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.67.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.67.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.67.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.68.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.68.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.68.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.68.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.68.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.69.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.69.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.69.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.69.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.69.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.7.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.7.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.7.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.7.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.7.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.70.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.70.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.70.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.70.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.70.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.71.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.71.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.71.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.71.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.71.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.8.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.8.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.8.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.8.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.8.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.9.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.9.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.9.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.9.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.9.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.router.layer.weight": "model-00004-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.21.mamba.A_log": "model-00004-of-00007.safetensors", "model.layers.21.mamba.D": "model-00004-of-00007.safetensors", "model.layers.21.mamba.conv1d.bias": "model-00004-of-00007.safetensors", "model.layers.21.mamba.conv1d.weight": "model-00004-of-00007.safetensors", "model.layers.21.mamba.dt_bias": "model-00004-of-00007.safetensors", "model.layers.21.mamba.in_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.mamba.in_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.mamba.in_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.mamba.norm.weight": "model-00004-of-00007.safetensors", "model.layers.21.mamba.out_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.mamba.out_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.mamba.out_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.21.shared_mlp.input_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.shared_mlp.input_linear.weight": "model-00004-of-00007.safetensors", "model.layers.21.shared_mlp.input_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.21.shared_mlp.output_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.21.shared_mlp.output_linear.weight": "model-00004-of-00007.safetensors", "model.layers.21.shared_mlp.output_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.10.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.10.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.10.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.10.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.10.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.11.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.11.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.11.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.11.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.11.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.12.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.12.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.12.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.12.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.12.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.13.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.13.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.13.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.13.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.13.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.14.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.14.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.14.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.14.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.14.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.15.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.15.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.15.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.15.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.15.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.16.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.16.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.16.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.16.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.16.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.17.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.17.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.17.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.17.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.17.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.18.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.18.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.18.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.18.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.18.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.19.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.19.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.19.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.19.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.19.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.20.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.20.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.20.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.20.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.20.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.21.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.21.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.21.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.21.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.21.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.22.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.22.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.22.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.22.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.22.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.23.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.23.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.23.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.23.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.23.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.24.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.24.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.24.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.24.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.24.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.25.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.25.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.25.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.25.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.25.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.26.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.26.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.26.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.26.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.26.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.27.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.27.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.27.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.27.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.27.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.28.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.28.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.28.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.28.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.28.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.29.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.29.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.29.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.29.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.29.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.30.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.30.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.30.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.30.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.30.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.31.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.31.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.31.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.31.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.31.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.32.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.32.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.32.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.32.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.32.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.33.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.33.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.33.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.33.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.33.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.34.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.34.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.34.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.34.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.34.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.35.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.35.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.35.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.35.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.35.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.36.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.36.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.36.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.36.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.36.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.37.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.37.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.37.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.37.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.37.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.38.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.38.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.38.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.38.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.38.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.39.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.39.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.39.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.39.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.39.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.4.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.4.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.4.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.4.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.4.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.40.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.40.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.40.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.40.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.40.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.41.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.41.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.41.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.41.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.41.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.42.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.42.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.42.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.42.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.42.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.43.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.43.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.43.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.43.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.43.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.44.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.44.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.44.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.44.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.44.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.45.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.45.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.45.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.45.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.45.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.46.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.46.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.46.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.46.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.46.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.47.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.47.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.47.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.47.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.47.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.48.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.48.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.48.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.48.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.48.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.49.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.49.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.49.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.49.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.49.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.5.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.5.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.5.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.5.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.5.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.50.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.50.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.50.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.50.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.50.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.51.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.51.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.51.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.51.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.51.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.52.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.52.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.52.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.52.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.52.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.53.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.53.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.53.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.53.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.53.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.54.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.54.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.54.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.54.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.54.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.55.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.55.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.55.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.55.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.55.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.56.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.56.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.56.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.56.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.56.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.57.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.57.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.57.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.57.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.57.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.58.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.58.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.58.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.58.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.58.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.59.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.59.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.59.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.59.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.59.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.6.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.6.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.6.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.6.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.6.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.60.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.60.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.60.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.60.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.60.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.61.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.61.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.61.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.61.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.61.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.62.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.62.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.62.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.62.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.62.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.63.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.63.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.63.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.63.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.63.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.64.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.64.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.64.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.64.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.64.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.65.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.65.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.65.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.65.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.65.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.66.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.66.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.66.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.66.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.66.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.67.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.67.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.67.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.67.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.67.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.68.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.68.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.68.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.68.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.68.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.69.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.69.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.69.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.69.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.69.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.7.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.7.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.7.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.7.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.7.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.70.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.70.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.70.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.70.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.70.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.71.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.71.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.71.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.71.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.71.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.8.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.8.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.8.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.8.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.8.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.9.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.9.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.9.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.9.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.9.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.router.layer.weight": "model-00004-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.mamba.A_log": "model-00004-of-00007.safetensors", "model.layers.22.mamba.D": "model-00004-of-00007.safetensors", "model.layers.22.mamba.conv1d.bias": "model-00004-of-00007.safetensors", "model.layers.22.mamba.conv1d.weight": "model-00004-of-00007.safetensors", "model.layers.22.mamba.dt_bias": "model-00004-of-00007.safetensors", "model.layers.22.mamba.in_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.mamba.in_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mamba.in_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.mamba.norm.weight": "model-00004-of-00007.safetensors", "model.layers.22.mamba.out_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.mamba.out_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mamba.out_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.shared_mlp.input_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.shared_mlp.input_linear.weight": "model-00004-of-00007.safetensors", "model.layers.22.shared_mlp.input_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.22.shared_mlp.output_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.22.shared_mlp.output_linear.weight": "model-00004-of-00007.safetensors", "model.layers.22.shared_mlp.output_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.10.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.10.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.10.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.10.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.10.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.11.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.11.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.11.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.11.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.11.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.12.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.12.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.12.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.12.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.12.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.13.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.13.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.13.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.13.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.13.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.14.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.14.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.14.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.14.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.14.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.15.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.15.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.15.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.15.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.15.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.16.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.16.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.16.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.16.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.16.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.17.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.17.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.17.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.17.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.17.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.18.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.18.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.18.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.18.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.18.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.19.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.19.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.19.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.19.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.19.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.20.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.20.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.20.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.20.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.20.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.21.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.21.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.21.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.21.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.21.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.22.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.22.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.22.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.22.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.22.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.23.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.23.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.23.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.23.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.23.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.24.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.24.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.24.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.24.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.24.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.25.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.25.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.25.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.25.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.25.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.26.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.26.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.26.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.26.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.26.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.27.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.27.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.27.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.27.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.27.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.28.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.28.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.28.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.28.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.28.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.29.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.29.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.29.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.29.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.29.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.30.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.30.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.30.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.30.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.30.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.31.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.31.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.31.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.31.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.31.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.32.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.32.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.32.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.32.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.32.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.33.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.33.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.33.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.33.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.33.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.34.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.34.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.34.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.34.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.34.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.35.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.35.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.35.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.35.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.35.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.36.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.36.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.36.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.36.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.36.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.37.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.37.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.37.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.37.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.37.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.38.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.38.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.38.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.38.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.38.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.39.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.39.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.39.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.39.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.39.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.4.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.4.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.4.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.4.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.4.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.40.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.40.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.40.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.40.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.40.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.41.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.41.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.41.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.41.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.41.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.42.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.42.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.42.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.42.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.42.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.43.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.43.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.43.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.43.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.43.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.44.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.44.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.44.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.44.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.44.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.45.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.45.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.45.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.45.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.45.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.46.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.46.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.46.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.46.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.46.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.47.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.47.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.47.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.47.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.47.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.48.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.48.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.48.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.48.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.48.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.49.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.49.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.49.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.49.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.49.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.5.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.5.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.5.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.5.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.5.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.50.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.50.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.50.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.50.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.50.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.51.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.51.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.51.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.51.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.51.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.52.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.52.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.52.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.52.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.52.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.53.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.53.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.53.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.53.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.53.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.54.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.54.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.54.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.54.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.54.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.55.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.55.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.55.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.55.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.55.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.56.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.56.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.56.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.56.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.56.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.57.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.57.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.57.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.57.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.57.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.58.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.58.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.58.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.58.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.58.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.59.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.59.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.59.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.59.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.59.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.6.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.6.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.6.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.6.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.6.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.60.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.60.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.60.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.60.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.60.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.61.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.61.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.61.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.61.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.61.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.62.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.62.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.62.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.62.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.62.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.63.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.63.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.63.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.63.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.63.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.64.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.64.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.64.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.64.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.64.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.65.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.65.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.65.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.65.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.65.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.66.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.66.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.66.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.66.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.66.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.67.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.67.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.67.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.67.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.67.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.68.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.68.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.68.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.68.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.68.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.69.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.69.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.69.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.69.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.69.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.7.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.7.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.7.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.7.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.7.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.70.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.70.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.70.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.70.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.70.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.71.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.71.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.71.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.71.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.71.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.8.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.8.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.8.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.8.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.8.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.9.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.9.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.9.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.9.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.9.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.router.layer.weight": "model-00004-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.mamba.A_log": "model-00004-of-00007.safetensors", "model.layers.23.mamba.D": "model-00004-of-00007.safetensors", "model.layers.23.mamba.conv1d.bias": "model-00004-of-00007.safetensors", "model.layers.23.mamba.conv1d.weight": "model-00004-of-00007.safetensors", "model.layers.23.mamba.dt_bias": "model-00004-of-00007.safetensors", "model.layers.23.mamba.in_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.mamba.in_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mamba.in_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.mamba.norm.weight": "model-00004-of-00007.safetensors", "model.layers.23.mamba.out_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.mamba.out_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mamba.out_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.shared_mlp.input_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.shared_mlp.input_linear.weight": "model-00004-of-00007.safetensors", "model.layers.23.shared_mlp.input_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.23.shared_mlp.output_linear.input_scale": "model-00004-of-00007.safetensors", "model.layers.23.shared_mlp.output_linear.weight": "model-00004-of-00007.safetensors", "model.layers.23.shared_mlp.output_linear.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.10.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.10.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.10.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.10.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.10.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.11.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.11.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.11.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.11.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.11.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.12.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.12.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.12.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.12.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.12.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.13.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.13.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.13.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.13.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.13.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.14.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.14.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.14.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.14.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.14.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.15.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.15.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.15.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.15.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.15.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.16.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.16.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.16.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.16.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.16.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.17.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.17.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.17.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.17.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.17.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.18.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.18.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.18.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.18.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.18.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.19.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.19.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.19.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.19.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.19.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.20.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.20.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.20.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.20.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.20.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.21.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.21.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.21.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.21.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.21.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.22.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.22.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.22.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.22.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.22.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.23.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.23.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.23.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.23.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.23.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.24.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.24.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.24.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.24.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.24.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.25.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.25.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.25.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.25.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.25.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.26.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.26.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.26.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.26.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.26.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.27.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.27.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.27.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.27.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.27.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.28.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.28.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.28.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.28.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.28.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.29.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.29.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.29.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.29.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.29.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.30.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.30.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.30.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.30.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.30.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.31.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.31.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.31.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.31.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.31.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.32.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.32.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.32.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.32.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.32.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.33.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.33.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.33.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.33.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.33.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.34.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.34.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.34.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.34.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.34.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.35.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.35.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.35.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.35.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.35.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.36.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.36.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.36.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.36.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.36.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.37.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.37.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.37.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.37.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.37.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.38.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.38.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.38.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.38.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.38.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.39.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.39.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.39.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.39.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.39.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.4.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.4.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.4.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.4.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.4.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.40.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.40.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.40.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.40.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.40.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.41.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.41.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.41.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.41.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.41.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.42.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.42.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.42.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.42.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.42.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.43.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.43.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.43.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.43.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.43.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.44.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.44.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.44.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.44.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.44.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.45.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.45.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.45.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.45.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.45.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.46.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.46.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.46.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.46.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.46.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.47.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.47.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.47.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.47.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.47.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.48.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.48.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.48.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.48.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.48.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.49.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.49.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.49.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.49.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.49.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.5.down_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.5.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.5.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.5.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.5.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.50.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.50.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.50.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.50.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.50.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.51.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.51.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.51.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.51.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.51.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.52.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.52.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.52.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.52.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.52.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.53.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.53.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.53.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.53.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.53.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.54.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.54.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.54.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.54.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.54.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.55.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.55.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.55.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.55.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.55.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.56.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.56.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.56.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.56.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.56.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.57.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.57.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.57.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.57.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.57.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.58.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.58.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.58.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.58.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.58.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.59.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.59.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.59.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.59.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.59.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.6.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.6.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.6.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.6.up_proj.input_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.6.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.60.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.60.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.60.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.60.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.60.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.61.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.61.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.61.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.61.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.61.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.62.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.62.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.62.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.62.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.62.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.63.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.63.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.63.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.63.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.63.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.64.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.64.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.64.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.64.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.64.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.65.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.65.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.65.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.65.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.65.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.66.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.66.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.66.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.66.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.66.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.67.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.67.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.67.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.67.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.67.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.68.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.68.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.68.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.68.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.68.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.69.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.69.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.69.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.69.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.69.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.7.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.7.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.7.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.7.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.7.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.70.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.70.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.70.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.70.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.70.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.71.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.71.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.71.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.71.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.71.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.8.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.8.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.8.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.8.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.8.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.9.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.9.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.9.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.9.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.9.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.router.layer.weight": "model-00004-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.24.mamba.A_log": "model-00005-of-00007.safetensors", "model.layers.24.mamba.D": "model-00005-of-00007.safetensors", "model.layers.24.mamba.conv1d.bias": "model-00005-of-00007.safetensors", "model.layers.24.mamba.conv1d.weight": "model-00005-of-00007.safetensors", "model.layers.24.mamba.dt_bias": "model-00005-of-00007.safetensors", "model.layers.24.mamba.in_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.mamba.in_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.mamba.in_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.mamba.norm.weight": "model-00005-of-00007.safetensors", "model.layers.24.mamba.out_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.mamba.out_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.mamba.out_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.24.shared_mlp.input_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.shared_mlp.input_linear.weight": "model-00005-of-00007.safetensors", "model.layers.24.shared_mlp.input_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.24.shared_mlp.output_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.24.shared_mlp.output_linear.weight": "model-00005-of-00007.safetensors", "model.layers.24.shared_mlp.output_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.10.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.10.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.10.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.10.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.10.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.11.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.11.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.11.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.11.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.11.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.12.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.12.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.12.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.12.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.12.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.13.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.13.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.13.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.13.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.13.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.14.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.14.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.14.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.14.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.14.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.15.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.15.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.15.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.15.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.15.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.16.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.16.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.16.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.16.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.16.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.17.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.17.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.17.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.17.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.17.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.18.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.18.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.18.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.18.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.18.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.19.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.19.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.19.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.19.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.19.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.20.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.20.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.20.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.20.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.20.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.21.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.21.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.21.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.21.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.21.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.22.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.22.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.22.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.22.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.22.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.23.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.23.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.23.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.23.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.23.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.24.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.24.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.24.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.24.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.24.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.25.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.25.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.25.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.25.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.25.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.26.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.26.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.26.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.26.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.26.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.27.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.27.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.27.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.27.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.27.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.28.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.28.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.28.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.28.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.28.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.29.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.29.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.29.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.29.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.29.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.30.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.30.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.30.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.30.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.30.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.31.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.31.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.31.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.31.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.31.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.32.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.32.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.32.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.32.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.32.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.33.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.33.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.33.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.33.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.33.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.34.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.34.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.34.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.34.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.34.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.35.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.35.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.35.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.35.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.35.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.36.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.36.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.36.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.36.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.36.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.37.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.37.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.37.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.37.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.37.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.38.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.38.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.38.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.38.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.38.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.39.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.39.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.39.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.39.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.39.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.4.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.4.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.4.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.4.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.4.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.40.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.40.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.40.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.40.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.40.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.41.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.41.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.41.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.41.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.41.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.42.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.42.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.42.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.42.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.42.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.43.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.43.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.43.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.43.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.43.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.44.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.44.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.44.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.44.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.44.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.45.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.45.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.45.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.45.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.45.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.46.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.46.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.46.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.46.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.46.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.47.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.47.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.47.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.47.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.47.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.48.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.48.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.48.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.48.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.48.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.49.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.49.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.49.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.49.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.49.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.5.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.5.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.5.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.5.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.5.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.50.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.50.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.50.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.50.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.50.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.51.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.51.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.51.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.51.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.51.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.52.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.52.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.52.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.52.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.52.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.53.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.53.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.53.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.53.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.53.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.54.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.54.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.54.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.54.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.54.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.55.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.55.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.55.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.55.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.55.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.56.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.56.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.56.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.56.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.56.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.57.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.57.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.57.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.57.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.57.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.58.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.58.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.58.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.58.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.58.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.59.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.59.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.59.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.59.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.59.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.6.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.6.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.6.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.6.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.6.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.60.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.60.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.60.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.60.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.60.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.61.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.61.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.61.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.61.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.61.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.62.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.62.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.62.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.62.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.62.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.63.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.63.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.63.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.63.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.63.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.64.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.64.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.64.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.64.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.64.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.65.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.65.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.65.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.65.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.65.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.66.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.66.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.66.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.66.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.66.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.67.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.67.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.67.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.67.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.67.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.68.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.68.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.68.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.68.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.68.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.69.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.69.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.69.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.69.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.69.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.7.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.7.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.7.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.7.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.7.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.70.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.70.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.70.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.70.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.70.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.71.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.71.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.71.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.71.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.71.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.8.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.8.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.8.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.8.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.8.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.9.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.9.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.9.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.9.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.9.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.router.layer.weight": "model-00005-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.k_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.k_proj.output_scale": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.o_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.q_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.v_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.v_proj.output_scale": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.shared_mlp.input_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.shared_mlp.input_linear.weight": "model-00005-of-00007.safetensors", "model.layers.25.shared_mlp.input_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.25.shared_mlp.output_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.25.shared_mlp.output_linear.weight": "model-00005-of-00007.safetensors", "model.layers.25.shared_mlp.output_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.10.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.10.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.10.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.10.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.10.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.11.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.11.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.11.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.11.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.11.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.12.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.12.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.12.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.12.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.12.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.13.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.13.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.13.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.13.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.13.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.14.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.14.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.14.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.14.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.14.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.15.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.15.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.15.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.15.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.15.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.16.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.16.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.16.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.16.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.16.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.17.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.17.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.17.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.17.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.17.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.18.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.18.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.18.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.18.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.18.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.19.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.19.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.19.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.19.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.19.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.20.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.20.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.20.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.20.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.20.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.21.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.21.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.21.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.21.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.21.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.22.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.22.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.22.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.22.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.22.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.23.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.23.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.23.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.23.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.23.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.24.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.24.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.24.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.24.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.24.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.25.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.25.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.25.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.25.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.25.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.26.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.26.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.26.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.26.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.26.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.27.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.27.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.27.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.27.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.27.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.28.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.28.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.28.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.28.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.28.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.29.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.29.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.29.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.29.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.29.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.30.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.30.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.30.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.30.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.30.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.31.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.31.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.31.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.31.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.31.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.32.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.32.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.32.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.32.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.32.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.33.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.33.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.33.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.33.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.33.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.34.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.34.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.34.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.34.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.34.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.35.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.35.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.35.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.35.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.35.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.36.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.36.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.36.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.36.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.36.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.37.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.37.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.37.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.37.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.37.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.38.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.38.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.38.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.38.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.38.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.39.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.39.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.39.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.39.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.39.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.4.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.4.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.4.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.4.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.4.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.40.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.40.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.40.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.40.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.40.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.41.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.41.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.41.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.41.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.41.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.42.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.42.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.42.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.42.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.42.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.43.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.43.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.43.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.43.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.43.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.44.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.44.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.44.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.44.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.44.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.45.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.45.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.45.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.45.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.45.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.46.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.46.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.46.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.46.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.46.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.47.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.47.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.47.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.47.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.47.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.48.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.48.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.48.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.48.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.48.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.49.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.49.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.49.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.49.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.49.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.5.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.5.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.5.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.5.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.5.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.50.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.50.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.50.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.50.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.50.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.51.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.51.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.51.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.51.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.51.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.52.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.52.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.52.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.52.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.52.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.53.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.53.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.53.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.53.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.53.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.54.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.54.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.54.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.54.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.54.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.55.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.55.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.55.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.55.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.55.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.56.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.56.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.56.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.56.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.56.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.57.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.57.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.57.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.57.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.57.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.58.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.58.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.58.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.58.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.58.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.59.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.59.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.59.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.59.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.59.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.6.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.6.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.6.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.6.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.6.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.60.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.60.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.60.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.60.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.60.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.61.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.61.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.61.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.61.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.61.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.62.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.62.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.62.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.62.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.62.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.63.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.63.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.63.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.63.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.63.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.64.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.64.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.64.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.64.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.64.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.65.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.65.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.65.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.65.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.65.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.66.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.66.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.66.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.66.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.66.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.67.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.67.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.67.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.67.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.67.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.68.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.68.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.68.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.68.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.68.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.69.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.69.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.69.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.69.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.69.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.7.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.7.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.7.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.7.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.7.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.70.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.70.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.70.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.70.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.70.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.71.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.71.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.71.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.71.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.71.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.8.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.8.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.8.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.8.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.8.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.9.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.9.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.9.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.9.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.9.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.router.layer.weight": "model-00005-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.26.mamba.A_log": "model-00005-of-00007.safetensors", "model.layers.26.mamba.D": "model-00005-of-00007.safetensors", "model.layers.26.mamba.conv1d.bias": "model-00005-of-00007.safetensors", "model.layers.26.mamba.conv1d.weight": "model-00005-of-00007.safetensors", "model.layers.26.mamba.dt_bias": "model-00005-of-00007.safetensors", "model.layers.26.mamba.in_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.mamba.in_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.mamba.in_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.mamba.norm.weight": "model-00005-of-00007.safetensors", "model.layers.26.mamba.out_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.mamba.out_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.mamba.out_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.26.shared_mlp.input_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.shared_mlp.input_linear.weight": "model-00005-of-00007.safetensors", "model.layers.26.shared_mlp.input_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.26.shared_mlp.output_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.26.shared_mlp.output_linear.weight": "model-00005-of-00007.safetensors", "model.layers.26.shared_mlp.output_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.10.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.10.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.10.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.10.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.10.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.11.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.11.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.11.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.11.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.11.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.12.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.12.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.12.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.12.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.12.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.13.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.13.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.13.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.13.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.13.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.14.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.14.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.14.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.14.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.14.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.15.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.15.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.15.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.15.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.15.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.16.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.16.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.16.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.16.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.16.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.17.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.17.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.17.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.17.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.17.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.18.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.18.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.18.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.18.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.18.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.19.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.19.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.19.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.19.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.19.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.20.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.20.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.20.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.20.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.20.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.21.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.21.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.21.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.21.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.21.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.22.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.22.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.22.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.22.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.22.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.23.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.23.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.23.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.23.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.23.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.24.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.24.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.24.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.24.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.24.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.25.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.25.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.25.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.25.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.25.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.26.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.26.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.26.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.26.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.26.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.27.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.27.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.27.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.27.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.27.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.28.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.28.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.28.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.28.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.28.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.29.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.29.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.29.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.29.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.29.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.30.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.30.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.30.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.30.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.30.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.31.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.31.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.31.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.31.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.31.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.32.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.32.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.32.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.32.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.32.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.33.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.33.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.33.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.33.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.33.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.34.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.34.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.34.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.34.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.34.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.35.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.35.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.35.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.35.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.35.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.36.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.36.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.36.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.36.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.36.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.37.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.37.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.37.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.37.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.37.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.38.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.38.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.38.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.38.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.38.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.39.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.39.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.39.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.39.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.39.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.4.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.4.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.4.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.4.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.4.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.40.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.40.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.40.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.40.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.40.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.41.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.41.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.41.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.41.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.41.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.42.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.42.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.42.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.42.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.42.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.43.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.43.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.43.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.43.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.43.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.44.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.44.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.44.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.44.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.44.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.45.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.45.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.45.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.45.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.45.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.46.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.46.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.46.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.46.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.46.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.47.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.47.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.47.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.47.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.47.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.48.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.48.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.48.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.48.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.48.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.49.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.49.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.49.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.49.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.49.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.5.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.5.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.5.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.5.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.5.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.50.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.50.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.50.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.50.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.50.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.51.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.51.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.51.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.51.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.51.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.52.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.52.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.52.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.52.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.52.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.53.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.53.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.53.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.53.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.53.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.54.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.54.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.54.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.54.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.54.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.55.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.55.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.55.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.55.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.55.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.56.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.56.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.56.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.56.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.56.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.57.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.57.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.57.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.57.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.57.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.58.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.58.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.58.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.58.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.58.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.59.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.59.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.59.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.59.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.59.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.6.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.6.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.6.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.6.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.6.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.60.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.60.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.60.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.60.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.60.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.61.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.61.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.61.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.61.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.61.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.62.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.62.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.62.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.62.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.62.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.63.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.63.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.63.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.63.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.63.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.64.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.64.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.64.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.64.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.64.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.65.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.65.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.65.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.65.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.65.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.66.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.66.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.66.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.66.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.66.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.67.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.67.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.67.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.67.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.67.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.68.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.68.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.68.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.68.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.68.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.69.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.69.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.69.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.69.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.69.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.7.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.7.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.7.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.7.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.7.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.70.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.70.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.70.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.70.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.70.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.71.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.71.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.71.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.71.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.71.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.8.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.8.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.8.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.8.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.8.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.9.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.9.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.9.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.9.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.9.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.router.layer.weight": "model-00005-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.27.mamba.A_log": "model-00005-of-00007.safetensors", "model.layers.27.mamba.D": "model-00005-of-00007.safetensors", "model.layers.27.mamba.conv1d.bias": "model-00005-of-00007.safetensors", "model.layers.27.mamba.conv1d.weight": "model-00005-of-00007.safetensors", "model.layers.27.mamba.dt_bias": "model-00005-of-00007.safetensors", "model.layers.27.mamba.in_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.mamba.in_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.mamba.in_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.mamba.norm.weight": "model-00005-of-00007.safetensors", "model.layers.27.mamba.out_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.mamba.out_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.mamba.out_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.27.shared_mlp.input_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.shared_mlp.input_linear.weight": "model-00005-of-00007.safetensors", "model.layers.27.shared_mlp.input_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.27.shared_mlp.output_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.27.shared_mlp.output_linear.weight": "model-00005-of-00007.safetensors", "model.layers.27.shared_mlp.output_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.10.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.10.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.10.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.10.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.10.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.11.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.11.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.11.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.11.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.11.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.12.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.12.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.12.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.12.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.12.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.13.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.13.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.13.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.13.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.13.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.14.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.14.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.14.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.14.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.14.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.15.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.15.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.15.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.15.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.15.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.16.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.16.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.16.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.16.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.16.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.17.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.17.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.17.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.17.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.17.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.18.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.18.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.18.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.18.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.18.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.19.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.19.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.19.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.19.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.19.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.20.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.20.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.20.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.20.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.20.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.21.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.21.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.21.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.21.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.21.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.22.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.22.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.22.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.22.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.22.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.23.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.23.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.23.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.23.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.23.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.24.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.24.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.24.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.24.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.24.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.25.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.25.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.25.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.25.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.25.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.26.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.26.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.26.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.26.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.26.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.27.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.27.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.27.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.27.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.27.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.28.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.28.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.28.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.28.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.28.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.29.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.29.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.29.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.29.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.29.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.30.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.30.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.30.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.30.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.30.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.31.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.31.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.31.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.31.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.31.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.32.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.32.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.32.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.32.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.32.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.33.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.33.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.33.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.33.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.33.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.34.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.34.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.34.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.34.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.34.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.35.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.35.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.35.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.35.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.35.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.36.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.36.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.36.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.36.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.36.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.37.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.37.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.37.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.37.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.37.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.38.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.38.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.38.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.38.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.38.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.39.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.39.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.39.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.39.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.39.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.4.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.4.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.4.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.4.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.4.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.40.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.40.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.40.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.40.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.40.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.41.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.41.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.41.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.41.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.41.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.42.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.42.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.42.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.42.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.42.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.43.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.43.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.43.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.43.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.43.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.44.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.44.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.44.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.44.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.44.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.45.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.45.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.45.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.45.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.45.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.46.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.46.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.46.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.46.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.46.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.47.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.47.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.47.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.47.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.47.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.48.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.48.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.48.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.48.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.48.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.49.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.49.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.49.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.49.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.49.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.5.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.5.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.5.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.5.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.5.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.50.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.50.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.50.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.50.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.50.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.51.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.51.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.51.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.51.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.51.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.52.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.52.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.52.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.52.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.52.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.53.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.53.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.53.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.53.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.53.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.54.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.54.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.54.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.54.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.54.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.55.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.55.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.55.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.55.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.55.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.56.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.56.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.56.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.56.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.56.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.57.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.57.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.57.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.57.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.57.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.58.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.58.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.58.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.58.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.58.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.59.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.59.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.59.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.59.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.59.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.6.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.6.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.6.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.6.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.6.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.60.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.60.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.60.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.60.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.60.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.61.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.61.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.61.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.61.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.61.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.62.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.62.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.62.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.62.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.62.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.63.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.63.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.63.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.63.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.63.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.64.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.64.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.64.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.64.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.64.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.65.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.65.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.65.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.65.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.65.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.66.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.66.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.66.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.66.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.66.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.67.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.67.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.67.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.67.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.67.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.68.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.68.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.68.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.68.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.68.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.69.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.69.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.69.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.69.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.69.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.7.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.7.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.7.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.7.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.7.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.70.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.70.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.70.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.70.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.70.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.71.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.71.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.71.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.71.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.71.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.8.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.8.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.8.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.8.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.8.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.9.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.9.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.9.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.9.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.9.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.router.layer.weight": "model-00005-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.28.mamba.A_log": "model-00005-of-00007.safetensors", "model.layers.28.mamba.D": "model-00005-of-00007.safetensors", "model.layers.28.mamba.conv1d.bias": "model-00005-of-00007.safetensors", "model.layers.28.mamba.conv1d.weight": "model-00005-of-00007.safetensors", "model.layers.28.mamba.dt_bias": "model-00005-of-00007.safetensors", "model.layers.28.mamba.in_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.mamba.in_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.mamba.in_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.mamba.norm.weight": "model-00005-of-00007.safetensors", "model.layers.28.mamba.out_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.mamba.out_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.mamba.out_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.28.shared_mlp.input_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.shared_mlp.input_linear.weight": "model-00005-of-00007.safetensors", "model.layers.28.shared_mlp.input_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.28.shared_mlp.output_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.28.shared_mlp.output_linear.weight": "model-00005-of-00007.safetensors", "model.layers.28.shared_mlp.output_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.10.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.10.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.10.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.10.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.10.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.11.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.11.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.11.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.11.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.11.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.12.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.12.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.12.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.12.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.12.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.13.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.13.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.13.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.13.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.13.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.14.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.14.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.14.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.14.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.14.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.15.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.15.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.15.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.15.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.15.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.16.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.16.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.16.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.16.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.16.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.17.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.17.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.17.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.17.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.17.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.18.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.18.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.18.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.18.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.18.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.19.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.19.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.19.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.19.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.19.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.20.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.20.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.20.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.20.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.20.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.21.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.21.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.21.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.21.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.21.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.22.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.22.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.22.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.22.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.22.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.23.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.23.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.23.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.23.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.23.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.24.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.24.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.24.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.24.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.24.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.25.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.25.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.25.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.25.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.25.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.26.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.26.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.26.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.26.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.26.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.27.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.27.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.27.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.27.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.27.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.28.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.28.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.28.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.28.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.28.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.29.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.29.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.29.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.29.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.29.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.30.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.30.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.30.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.30.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.30.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.31.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.31.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.31.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.31.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.31.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.32.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.32.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.32.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.32.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.32.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.33.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.33.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.33.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.33.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.33.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.34.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.34.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.34.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.34.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.34.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.35.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.35.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.35.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.35.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.35.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.36.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.36.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.36.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.36.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.36.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.37.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.37.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.37.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.37.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.37.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.38.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.38.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.38.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.38.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.38.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.39.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.39.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.39.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.39.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.39.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.4.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.4.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.4.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.4.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.4.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.40.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.40.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.40.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.40.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.40.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.41.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.41.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.41.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.41.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.41.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.42.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.42.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.42.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.42.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.42.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.43.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.43.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.43.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.43.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.43.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.44.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.44.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.44.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.44.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.44.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.45.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.45.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.45.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.45.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.45.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.46.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.46.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.46.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.46.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.46.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.47.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.47.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.47.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.47.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.47.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.48.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.48.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.48.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.48.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.48.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.49.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.49.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.49.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.49.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.49.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.5.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.5.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.5.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.5.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.5.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.50.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.50.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.50.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.50.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.50.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.51.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.51.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.51.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.51.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.51.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.52.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.52.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.52.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.52.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.52.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.53.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.53.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.53.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.53.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.53.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.54.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.54.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.54.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.54.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.54.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.55.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.55.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.55.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.55.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.55.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.56.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.56.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.56.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.56.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.56.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.57.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.57.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.57.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.57.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.57.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.58.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.58.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.58.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.58.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.58.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.59.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.59.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.59.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.59.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.59.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.6.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.6.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.6.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.6.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.6.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.60.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.60.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.60.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.60.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.60.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.61.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.61.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.61.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.61.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.61.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.62.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.62.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.62.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.62.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.62.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.63.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.63.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.63.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.63.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.63.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.64.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.64.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.64.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.64.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.64.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.65.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.65.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.65.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.65.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.65.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.66.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.66.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.66.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.66.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.66.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.67.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.67.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.67.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.67.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.67.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.68.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.68.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.68.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.68.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.68.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.69.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.69.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.69.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.69.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.69.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.7.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.7.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.7.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.7.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.7.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.70.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.70.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.70.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.70.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.70.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.71.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.71.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.71.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.71.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.71.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.8.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.8.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.8.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.8.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.8.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.9.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.9.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.9.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.9.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.9.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.router.layer.weight": "model-00005-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.29.mamba.A_log": "model-00005-of-00007.safetensors", "model.layers.29.mamba.D": "model-00005-of-00007.safetensors", "model.layers.29.mamba.conv1d.bias": "model-00005-of-00007.safetensors", "model.layers.29.mamba.conv1d.weight": "model-00005-of-00007.safetensors", "model.layers.29.mamba.dt_bias": "model-00005-of-00007.safetensors", "model.layers.29.mamba.in_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.mamba.in_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.mamba.in_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.mamba.norm.weight": "model-00005-of-00007.safetensors", "model.layers.29.mamba.out_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.mamba.out_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.mamba.out_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.29.shared_mlp.input_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.shared_mlp.input_linear.weight": "model-00005-of-00007.safetensors", "model.layers.29.shared_mlp.input_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.29.shared_mlp.output_linear.input_scale": "model-00005-of-00007.safetensors", "model.layers.29.shared_mlp.output_linear.weight": "model-00005-of-00007.safetensors", "model.layers.29.shared_mlp.output_linear.weight_scale": "model-00005-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.10.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.10.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.10.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.10.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.10.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.11.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.11.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.11.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.11.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.11.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.12.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.12.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.12.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.12.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.12.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.13.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.13.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.13.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.13.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.13.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.14.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.14.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.14.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.14.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.14.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.15.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.15.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.15.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.15.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.15.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.16.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.16.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.16.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.16.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.16.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.17.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.17.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.17.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.17.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.17.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.18.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.18.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.18.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.18.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.18.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.19.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.19.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.19.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.19.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.19.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.20.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.20.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.20.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.20.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.20.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.21.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.21.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.21.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.21.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.21.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.22.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.22.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.22.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.22.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.22.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.23.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.23.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.23.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.23.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.23.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.24.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.24.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.24.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.24.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.24.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.25.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.25.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.25.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.25.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.25.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.26.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.26.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.26.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.26.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.26.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.27.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.27.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.27.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.27.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.27.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.28.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.28.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.28.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.28.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.28.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.29.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.29.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.29.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.29.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.29.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.30.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.30.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.30.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.30.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.30.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.31.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.31.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.31.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.31.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.31.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.32.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.32.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.32.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.32.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.32.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.33.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.33.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.33.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.33.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.33.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.34.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.34.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.34.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.34.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.34.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.35.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.35.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.35.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.35.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.35.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.36.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.36.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.36.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.36.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.36.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.37.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.37.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.37.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.37.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.37.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.38.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.38.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.38.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.38.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.38.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.39.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.39.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.39.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.39.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.39.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.4.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.4.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.4.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.4.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.4.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.40.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.40.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.40.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.40.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.40.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.41.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.41.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.41.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.41.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.41.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.42.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.42.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.42.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.42.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.42.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.43.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.43.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.43.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.43.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.43.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.44.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.44.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.44.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.44.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.44.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.45.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.45.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.45.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.45.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.45.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.46.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.46.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.46.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.46.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.46.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.47.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.47.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.47.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.47.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.47.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.48.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.48.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.48.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.48.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.48.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.49.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.49.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.49.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.49.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.49.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.5.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.5.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.5.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.5.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.5.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.50.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.50.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.50.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.50.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.50.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.51.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.51.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.51.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.51.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.51.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.52.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.52.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.52.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.52.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.52.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.53.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.53.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.53.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.53.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.53.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.54.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.54.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.54.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.54.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.54.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.55.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.55.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.55.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.55.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.55.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.56.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.56.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.56.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.56.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.56.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.57.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.57.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.57.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.57.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.57.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.58.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.58.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.58.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.58.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.58.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.59.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.59.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.59.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.59.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.59.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.6.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.6.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.6.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.6.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.6.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.60.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.60.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.60.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.60.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.60.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.61.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.61.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.61.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.61.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.61.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.62.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.62.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.62.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.62.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.62.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.63.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.63.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.63.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.63.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.63.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.64.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.64.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.64.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.64.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.64.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.65.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.65.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.65.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.65.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.65.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.66.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.66.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.66.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.66.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.66.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.67.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.67.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.67.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.67.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.67.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.68.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.68.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.68.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.68.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.68.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.69.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.69.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.69.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.69.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.69.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.7.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.7.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.7.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.7.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.7.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.70.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.70.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.70.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.70.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.70.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.71.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.71.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.71.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.71.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.71.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.8.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.8.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.8.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.8.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.8.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.9.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.9.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.9.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.9.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.9.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.router.layer.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.mamba.A_log": "model-00001-of-00007.safetensors", "model.layers.3.mamba.D": "model-00001-of-00007.safetensors", "model.layers.3.mamba.conv1d.bias": "model-00001-of-00007.safetensors", "model.layers.3.mamba.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.3.mamba.dt_bias": "model-00001-of-00007.safetensors", "model.layers.3.mamba.in_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.mamba.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mamba.in_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.mamba.norm.weight": "model-00001-of-00007.safetensors", "model.layers.3.mamba.out_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.mamba.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mamba.out_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.shared_mlp.input_linear.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.shared_mlp.input_linear.weight": "model-00001-of-00007.safetensors", "model.layers.3.shared_mlp.input_linear.weight_scale": "model-00001-of-00007.safetensors", "model.layers.3.shared_mlp.output_linear.input_scale": "model-00001-of-00007.safetensors", "model.layers.3.shared_mlp.output_linear.weight": "model-00001-of-00007.safetensors", "model.layers.3.shared_mlp.output_linear.weight_scale": "model-00001-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.10.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.10.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.10.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.10.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.10.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.11.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.11.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.11.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.11.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.11.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.12.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.12.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.12.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.12.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.12.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.13.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.13.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.13.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.13.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.13.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.14.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.14.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.14.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.14.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.14.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.15.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.15.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.15.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.15.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.15.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.16.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.16.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.16.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.16.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.16.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.17.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.17.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.17.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.17.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.17.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.18.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.18.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.18.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.18.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.18.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.19.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.19.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.19.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.19.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.19.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.20.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.20.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.20.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.20.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.20.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.21.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.21.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.21.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.21.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.21.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.22.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.22.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.22.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.22.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.22.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.23.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.23.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.23.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.23.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.23.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.24.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.24.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.24.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.24.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.24.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.25.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.25.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.25.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.25.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.25.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.26.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.26.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.26.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.26.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.26.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.27.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.27.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.27.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.27.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.27.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.28.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.28.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.28.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.28.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.28.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.29.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.29.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.29.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.29.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.29.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.30.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.30.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.30.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.30.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.30.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.31.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.31.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.31.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.31.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.31.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.32.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.32.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.32.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.32.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.32.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.33.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.33.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.33.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.33.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.33.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.34.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.34.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.34.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.34.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.34.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.35.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.35.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.35.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.35.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.35.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.36.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.36.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.36.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.36.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.36.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.37.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.37.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.37.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.37.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.37.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.38.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.38.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.38.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.38.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.38.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.39.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.39.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.39.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.39.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.39.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.4.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.4.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.4.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.4.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.4.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.40.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.40.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.40.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.40.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.40.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.41.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.41.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.41.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.41.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.41.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.42.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.42.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.42.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.42.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.42.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.43.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.43.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.43.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.43.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.43.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.44.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.44.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.44.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.44.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.44.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.45.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.45.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.45.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.45.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.45.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.46.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.46.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.46.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.46.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.46.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.47.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.47.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.47.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.47.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.47.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.48.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.48.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.48.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.48.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.48.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.49.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.49.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.49.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.49.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.49.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.5.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.5.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.5.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.5.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.5.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.50.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.50.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.50.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.50.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.50.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.51.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.51.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.51.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.51.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.51.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.52.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.52.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.52.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.52.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.52.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.53.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.53.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.53.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.53.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.53.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.54.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.54.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.54.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.54.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.55.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.55.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.56.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.56.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.57.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.57.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.58.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.58.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.59.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.59.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.6.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.6.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.6.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.6.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.6.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.60.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.60.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.60.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.60.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.60.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.61.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.61.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.61.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.61.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.61.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.62.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.62.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.62.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.62.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.62.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.63.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.63.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.63.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.63.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.63.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.64.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.64.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.64.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.64.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.64.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.65.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.65.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.65.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.65.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.65.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.66.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.66.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.66.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.66.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.66.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.67.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.67.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.67.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.67.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.67.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.68.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.68.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.68.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.68.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.68.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.69.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.69.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.69.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.69.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.69.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.7.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.7.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.7.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.7.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.7.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.70.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.70.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.70.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.70.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.70.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.71.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.71.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.71.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.71.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.71.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.8.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.8.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.8.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.8.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.8.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.9.down_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.9.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.9.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.9.up_proj.input_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.9.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.router.layer.weight": "model-00005-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.mamba.A_log": "model-00006-of-00007.safetensors", "model.layers.30.mamba.D": "model-00006-of-00007.safetensors", "model.layers.30.mamba.conv1d.bias": "model-00006-of-00007.safetensors", "model.layers.30.mamba.conv1d.weight": "model-00006-of-00007.safetensors", "model.layers.30.mamba.dt_bias": "model-00006-of-00007.safetensors", "model.layers.30.mamba.in_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.mamba.in_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.mamba.in_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.mamba.norm.weight": "model-00006-of-00007.safetensors", "model.layers.30.mamba.out_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.mamba.out_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.mamba.out_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.shared_mlp.input_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.shared_mlp.input_linear.weight": "model-00006-of-00007.safetensors", "model.layers.30.shared_mlp.input_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.30.shared_mlp.output_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.30.shared_mlp.output_linear.weight": "model-00006-of-00007.safetensors", "model.layers.30.shared_mlp.output_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.10.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.10.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.10.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.10.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.10.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.11.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.11.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.11.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.11.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.11.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.12.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.12.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.12.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.12.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.12.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.13.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.13.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.13.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.13.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.13.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.14.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.14.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.14.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.14.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.14.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.15.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.15.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.15.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.15.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.15.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.16.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.16.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.16.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.16.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.16.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.17.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.17.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.17.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.17.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.17.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.18.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.18.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.18.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.18.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.18.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.19.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.19.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.19.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.19.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.19.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.20.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.20.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.20.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.20.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.20.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.21.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.21.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.21.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.21.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.21.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.22.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.22.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.22.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.22.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.22.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.23.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.23.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.23.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.23.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.23.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.24.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.24.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.24.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.24.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.24.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.25.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.25.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.25.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.25.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.25.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.26.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.26.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.26.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.26.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.26.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.27.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.27.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.27.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.27.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.27.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.28.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.28.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.28.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.28.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.28.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.29.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.29.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.29.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.29.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.29.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.30.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.30.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.30.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.30.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.30.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.31.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.31.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.31.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.31.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.31.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.32.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.32.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.32.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.32.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.32.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.33.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.33.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.33.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.33.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.33.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.34.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.34.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.34.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.34.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.34.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.35.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.35.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.35.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.35.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.35.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.36.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.36.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.36.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.36.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.36.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.37.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.37.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.37.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.37.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.37.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.38.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.38.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.38.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.38.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.38.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.39.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.39.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.39.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.39.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.39.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.4.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.4.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.4.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.4.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.4.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.40.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.40.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.40.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.40.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.40.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.41.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.41.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.41.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.41.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.41.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.42.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.42.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.42.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.42.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.42.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.43.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.43.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.43.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.43.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.43.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.44.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.44.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.44.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.44.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.44.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.45.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.45.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.45.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.45.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.45.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.46.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.46.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.46.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.46.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.46.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.47.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.47.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.47.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.47.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.47.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.48.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.48.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.48.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.48.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.48.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.49.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.49.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.49.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.49.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.49.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.5.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.5.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.5.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.5.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.5.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.50.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.50.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.50.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.50.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.50.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.51.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.51.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.51.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.51.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.51.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.52.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.52.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.52.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.52.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.52.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.53.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.53.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.53.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.53.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.53.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.54.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.54.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.54.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.54.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.55.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.55.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.56.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.56.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.57.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.57.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.58.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.58.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.59.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.59.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.6.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.6.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.6.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.6.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.6.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.60.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.60.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.60.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.60.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.60.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.61.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.61.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.61.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.61.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.61.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.62.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.62.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.62.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.62.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.62.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.63.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.63.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.63.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.63.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.63.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.64.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.64.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.64.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.64.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.64.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.65.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.65.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.65.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.65.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.65.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.66.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.66.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.66.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.66.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.66.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.67.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.67.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.67.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.67.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.67.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.68.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.68.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.68.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.68.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.68.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.69.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.69.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.69.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.69.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.69.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.7.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.7.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.7.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.7.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.7.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.70.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.70.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.70.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.70.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.70.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.71.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.71.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.71.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.71.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.71.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.8.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.8.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.8.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.8.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.8.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.9.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.9.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.9.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.9.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.9.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.router.layer.weight": "model-00006-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.31.mamba.A_log": "model-00006-of-00007.safetensors", "model.layers.31.mamba.D": "model-00006-of-00007.safetensors", "model.layers.31.mamba.conv1d.bias": "model-00006-of-00007.safetensors", "model.layers.31.mamba.conv1d.weight": "model-00006-of-00007.safetensors", "model.layers.31.mamba.dt_bias": "model-00006-of-00007.safetensors", "model.layers.31.mamba.in_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.mamba.in_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.mamba.in_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.mamba.norm.weight": "model-00006-of-00007.safetensors", "model.layers.31.mamba.out_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.mamba.out_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.mamba.out_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.31.shared_mlp.input_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.shared_mlp.input_linear.weight": "model-00006-of-00007.safetensors", "model.layers.31.shared_mlp.input_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.31.shared_mlp.output_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.31.shared_mlp.output_linear.weight": "model-00006-of-00007.safetensors", "model.layers.31.shared_mlp.output_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.10.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.10.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.10.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.10.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.10.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.11.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.11.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.11.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.11.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.11.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.12.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.12.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.12.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.12.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.12.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.13.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.13.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.13.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.13.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.13.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.14.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.14.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.14.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.14.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.14.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.15.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.15.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.15.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.15.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.15.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.16.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.16.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.16.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.16.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.16.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.17.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.17.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.17.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.17.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.17.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.18.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.18.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.18.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.18.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.18.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.19.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.19.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.19.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.19.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.19.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.20.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.20.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.20.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.20.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.20.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.21.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.21.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.21.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.21.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.21.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.22.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.22.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.22.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.22.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.22.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.23.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.23.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.23.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.23.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.23.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.24.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.24.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.24.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.24.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.24.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.25.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.25.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.25.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.25.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.25.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.26.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.26.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.26.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.26.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.26.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.27.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.27.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.27.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.27.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.27.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.28.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.28.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.28.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.28.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.28.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.29.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.29.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.29.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.29.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.29.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.30.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.30.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.30.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.30.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.30.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.31.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.31.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.31.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.31.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.31.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.32.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.32.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.32.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.32.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.32.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.33.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.33.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.33.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.33.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.33.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.34.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.34.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.34.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.34.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.34.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.35.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.35.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.35.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.35.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.35.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.36.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.36.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.36.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.36.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.36.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.37.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.37.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.37.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.37.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.37.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.38.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.38.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.38.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.38.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.38.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.39.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.39.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.39.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.39.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.39.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.4.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.4.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.4.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.4.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.4.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.40.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.40.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.40.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.40.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.40.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.41.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.41.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.41.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.41.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.41.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.42.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.42.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.42.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.42.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.42.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.43.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.43.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.43.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.43.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.43.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.44.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.44.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.44.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.44.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.44.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.45.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.45.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.45.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.45.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.45.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.46.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.46.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.46.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.46.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.46.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.47.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.47.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.47.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.47.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.47.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.48.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.48.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.48.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.48.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.48.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.49.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.49.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.49.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.49.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.49.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.5.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.5.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.5.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.5.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.5.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.50.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.50.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.50.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.50.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.50.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.51.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.51.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.51.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.51.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.51.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.52.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.52.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.52.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.52.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.52.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.53.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.53.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.53.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.53.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.53.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.54.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.54.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.54.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.54.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.55.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.55.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.56.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.56.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.57.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.57.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.58.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.58.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.59.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.59.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.6.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.6.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.6.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.6.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.6.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.60.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.60.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.60.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.60.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.60.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.61.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.61.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.61.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.61.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.61.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.62.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.62.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.62.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.62.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.62.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.63.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.63.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.63.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.63.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.63.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.64.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.64.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.64.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.64.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.64.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.65.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.65.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.65.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.65.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.65.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.66.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.66.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.66.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.66.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.66.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.67.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.67.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.67.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.67.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.67.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.68.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.68.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.68.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.68.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.68.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.69.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.69.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.69.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.69.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.69.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.7.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.7.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.7.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.7.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.7.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.70.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.70.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.70.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.70.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.70.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.71.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.71.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.71.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.71.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.71.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.8.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.8.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.8.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.8.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.8.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.9.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.9.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.9.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.9.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.9.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.router.layer.weight": "model-00006-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.32.mamba.A_log": "model-00006-of-00007.safetensors", "model.layers.32.mamba.D": "model-00006-of-00007.safetensors", "model.layers.32.mamba.conv1d.bias": "model-00006-of-00007.safetensors", "model.layers.32.mamba.conv1d.weight": "model-00006-of-00007.safetensors", "model.layers.32.mamba.dt_bias": "model-00006-of-00007.safetensors", "model.layers.32.mamba.in_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.mamba.in_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.mamba.in_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.mamba.norm.weight": "model-00006-of-00007.safetensors", "model.layers.32.mamba.out_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.mamba.out_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.mamba.out_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.32.shared_mlp.input_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.shared_mlp.input_linear.weight": "model-00006-of-00007.safetensors", "model.layers.32.shared_mlp.input_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.32.shared_mlp.output_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.32.shared_mlp.output_linear.weight": "model-00006-of-00007.safetensors", "model.layers.32.shared_mlp.output_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.10.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.10.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.10.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.10.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.10.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.11.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.11.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.11.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.11.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.11.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.12.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.12.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.12.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.12.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.12.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.13.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.13.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.13.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.13.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.13.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.14.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.14.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.14.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.14.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.14.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.15.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.15.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.15.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.15.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.15.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.16.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.16.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.16.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.16.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.16.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.17.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.17.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.17.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.17.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.17.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.18.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.18.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.18.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.18.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.18.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.19.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.19.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.19.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.19.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.19.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.20.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.20.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.20.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.20.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.20.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.21.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.21.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.21.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.21.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.21.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.22.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.22.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.22.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.22.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.22.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.23.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.23.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.23.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.23.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.23.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.24.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.24.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.24.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.24.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.24.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.25.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.25.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.25.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.25.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.25.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.26.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.26.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.26.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.26.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.26.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.27.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.27.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.27.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.27.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.27.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.28.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.28.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.28.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.28.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.28.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.29.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.29.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.29.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.29.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.29.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.30.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.30.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.30.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.30.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.30.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.31.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.31.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.31.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.31.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.31.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.32.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.32.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.32.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.32.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.32.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.33.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.33.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.33.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.33.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.33.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.34.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.34.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.34.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.34.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.34.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.35.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.35.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.35.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.35.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.35.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.36.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.36.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.36.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.36.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.36.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.37.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.37.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.37.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.37.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.37.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.38.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.38.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.38.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.38.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.38.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.39.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.39.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.39.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.39.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.39.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.4.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.4.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.4.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.4.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.4.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.40.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.40.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.40.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.40.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.40.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.41.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.41.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.41.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.41.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.41.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.42.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.42.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.42.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.42.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.42.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.43.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.43.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.43.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.43.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.43.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.44.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.44.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.44.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.44.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.44.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.45.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.45.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.45.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.45.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.45.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.46.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.46.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.46.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.46.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.46.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.47.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.47.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.47.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.47.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.47.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.48.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.48.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.48.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.48.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.48.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.49.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.49.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.49.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.49.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.49.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.5.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.5.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.5.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.5.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.5.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.50.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.50.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.50.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.50.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.50.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.51.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.51.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.51.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.51.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.51.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.52.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.52.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.52.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.52.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.52.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.53.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.53.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.53.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.53.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.53.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.54.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.54.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.54.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.54.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.55.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.55.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.56.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.56.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.57.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.57.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.58.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.58.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.59.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.59.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.6.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.6.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.6.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.6.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.6.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.60.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.60.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.60.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.60.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.60.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.61.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.61.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.61.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.61.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.61.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.62.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.62.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.62.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.62.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.62.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.63.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.63.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.63.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.63.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.63.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.64.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.64.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.64.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.64.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.64.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.65.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.65.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.65.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.65.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.65.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.66.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.66.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.66.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.66.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.66.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.67.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.67.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.67.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.67.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.67.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.68.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.68.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.68.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.68.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.68.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.69.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.69.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.69.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.69.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.69.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.7.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.7.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.7.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.7.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.7.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.70.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.70.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.70.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.70.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.70.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.71.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.71.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.71.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.71.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.71.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.8.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.8.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.8.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.8.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.8.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.9.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.9.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.9.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.9.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.9.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.router.layer.weight": "model-00006-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.33.mamba.A_log": "model-00006-of-00007.safetensors", "model.layers.33.mamba.D": "model-00006-of-00007.safetensors", "model.layers.33.mamba.conv1d.bias": "model-00006-of-00007.safetensors", "model.layers.33.mamba.conv1d.weight": "model-00006-of-00007.safetensors", "model.layers.33.mamba.dt_bias": "model-00006-of-00007.safetensors", "model.layers.33.mamba.in_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.mamba.in_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.mamba.in_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.mamba.norm.weight": "model-00006-of-00007.safetensors", "model.layers.33.mamba.out_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.mamba.out_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.mamba.out_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.33.shared_mlp.input_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.shared_mlp.input_linear.weight": "model-00006-of-00007.safetensors", "model.layers.33.shared_mlp.input_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.33.shared_mlp.output_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.33.shared_mlp.output_linear.weight": "model-00006-of-00007.safetensors", "model.layers.33.shared_mlp.output_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.10.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.10.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.10.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.10.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.10.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.11.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.11.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.11.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.11.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.11.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.12.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.12.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.12.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.12.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.12.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.13.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.13.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.13.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.13.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.13.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.14.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.14.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.14.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.14.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.14.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.15.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.15.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.15.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.15.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.15.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.16.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.16.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.16.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.16.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.16.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.17.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.17.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.17.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.17.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.17.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.18.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.18.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.18.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.18.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.18.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.19.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.19.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.19.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.19.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.19.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.20.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.20.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.20.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.20.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.20.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.21.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.21.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.21.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.21.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.21.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.22.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.22.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.22.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.22.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.22.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.23.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.23.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.23.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.23.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.23.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.24.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.24.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.24.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.24.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.24.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.25.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.25.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.25.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.25.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.25.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.26.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.26.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.26.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.26.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.26.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.27.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.27.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.27.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.27.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.27.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.28.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.28.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.28.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.28.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.28.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.29.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.29.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.29.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.29.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.29.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.30.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.30.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.30.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.30.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.30.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.31.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.31.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.31.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.31.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.31.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.32.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.32.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.32.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.32.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.32.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.33.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.33.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.33.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.33.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.33.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.34.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.34.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.34.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.34.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.34.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.35.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.35.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.35.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.35.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.35.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.36.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.36.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.36.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.36.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.36.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.37.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.37.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.37.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.37.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.37.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.38.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.38.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.38.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.38.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.38.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.39.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.39.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.39.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.39.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.39.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.4.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.4.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.4.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.4.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.4.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.40.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.40.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.40.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.40.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.40.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.41.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.41.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.41.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.41.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.41.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.42.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.42.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.42.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.42.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.42.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.43.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.43.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.43.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.43.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.43.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.44.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.44.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.44.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.44.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.44.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.45.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.45.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.45.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.45.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.45.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.46.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.46.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.46.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.46.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.46.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.47.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.47.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.47.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.47.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.47.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.48.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.48.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.48.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.48.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.48.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.49.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.49.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.49.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.49.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.49.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.5.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.5.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.5.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.5.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.5.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.50.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.50.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.50.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.50.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.50.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.51.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.51.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.51.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.51.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.51.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.52.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.52.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.52.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.52.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.52.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.53.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.53.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.53.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.53.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.53.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.54.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.54.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.54.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.54.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.55.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.55.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.56.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.56.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.57.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.57.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.58.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.58.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.59.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.59.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.6.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.6.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.6.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.6.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.6.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.60.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.60.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.60.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.60.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.60.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.61.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.61.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.61.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.61.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.61.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.62.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.62.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.62.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.62.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.62.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.63.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.63.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.63.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.63.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.63.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.64.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.64.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.64.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.64.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.64.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.65.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.65.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.65.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.65.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.65.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.66.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.66.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.66.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.66.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.66.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.67.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.67.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.67.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.67.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.67.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.68.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.68.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.68.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.68.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.68.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.69.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.69.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.69.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.69.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.69.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.7.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.7.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.7.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.7.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.7.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.70.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.70.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.70.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.70.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.70.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.71.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.71.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.71.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.71.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.71.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.8.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.8.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.8.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.8.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.8.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.9.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.9.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.9.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.9.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.9.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.router.layer.weight": "model-00006-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.34.mamba.A_log": "model-00006-of-00007.safetensors", "model.layers.34.mamba.D": "model-00006-of-00007.safetensors", "model.layers.34.mamba.conv1d.bias": "model-00006-of-00007.safetensors", "model.layers.34.mamba.conv1d.weight": "model-00006-of-00007.safetensors", "model.layers.34.mamba.dt_bias": "model-00006-of-00007.safetensors", "model.layers.34.mamba.in_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.mamba.in_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.mamba.in_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.mamba.norm.weight": "model-00006-of-00007.safetensors", "model.layers.34.mamba.out_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.mamba.out_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.mamba.out_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.34.shared_mlp.input_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.shared_mlp.input_linear.weight": "model-00006-of-00007.safetensors", "model.layers.34.shared_mlp.input_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.34.shared_mlp.output_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.34.shared_mlp.output_linear.weight": "model-00006-of-00007.safetensors", "model.layers.34.shared_mlp.output_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.10.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.10.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.10.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.10.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.10.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.11.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.11.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.11.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.11.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.11.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.12.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.12.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.12.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.12.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.12.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.13.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.13.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.13.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.13.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.13.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.14.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.14.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.14.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.14.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.14.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.15.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.15.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.15.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.15.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.15.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.16.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.16.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.16.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.16.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.16.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.17.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.17.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.17.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.17.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.17.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.18.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.18.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.18.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.18.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.18.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.19.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.19.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.19.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.19.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.19.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.20.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.20.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.20.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.20.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.20.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.21.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.21.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.21.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.21.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.21.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.22.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.22.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.22.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.22.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.22.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.23.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.23.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.23.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.23.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.23.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.24.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.24.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.24.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.24.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.24.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.25.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.25.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.25.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.25.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.25.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.26.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.26.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.26.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.26.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.26.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.27.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.27.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.27.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.27.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.27.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.28.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.28.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.28.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.28.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.28.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.29.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.29.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.29.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.29.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.29.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.30.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.30.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.30.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.30.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.30.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.31.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.31.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.31.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.31.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.31.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.32.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.32.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.32.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.32.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.32.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.33.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.33.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.33.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.33.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.33.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.34.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.34.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.34.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.34.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.34.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.35.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.35.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.35.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.35.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.35.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.36.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.36.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.36.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.36.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.36.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.37.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.37.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.37.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.37.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.37.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.38.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.38.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.38.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.38.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.38.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.39.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.39.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.39.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.39.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.39.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.4.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.4.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.4.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.4.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.4.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.40.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.40.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.40.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.40.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.40.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.41.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.41.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.41.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.41.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.41.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.42.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.42.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.42.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.42.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.42.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.43.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.43.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.43.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.43.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.43.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.44.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.44.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.44.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.44.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.44.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.45.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.45.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.45.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.45.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.45.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.46.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.46.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.46.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.46.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.46.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.47.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.47.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.47.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.47.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.47.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.48.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.48.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.48.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.48.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.48.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.49.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.49.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.49.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.49.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.49.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.5.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.5.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.5.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.5.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.5.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.50.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.50.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.50.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.50.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.50.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.51.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.51.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.51.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.51.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.51.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.52.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.52.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.52.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.52.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.52.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.53.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.53.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.53.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.53.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.53.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.54.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.54.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.54.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.54.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.55.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.55.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.56.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.56.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.57.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.57.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.58.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.58.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.59.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.59.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.6.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.6.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.6.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.6.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.6.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.60.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.60.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.60.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.60.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.60.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.61.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.61.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.61.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.61.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.61.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.62.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.62.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.62.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.62.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.62.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.63.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.63.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.63.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.63.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.63.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.64.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.64.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.64.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.64.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.64.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.65.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.65.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.65.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.65.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.65.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.66.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.66.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.66.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.66.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.66.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.67.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.67.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.67.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.67.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.67.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.68.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.68.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.68.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.68.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.68.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.69.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.69.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.69.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.69.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.69.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.7.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.7.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.7.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.7.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.7.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.70.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.70.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.70.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.70.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.70.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.71.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.71.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.71.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.71.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.71.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.8.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.8.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.8.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.8.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.8.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.9.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.9.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.9.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.9.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.9.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.router.layer.weight": "model-00006-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.k_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.k_proj.output_scale": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.o_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.q_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.v_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.v_proj.output_scale": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.shared_mlp.input_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.shared_mlp.input_linear.weight": "model-00006-of-00007.safetensors", "model.layers.35.shared_mlp.input_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.35.shared_mlp.output_linear.input_scale": "model-00006-of-00007.safetensors", "model.layers.35.shared_mlp.output_linear.weight": "model-00006-of-00007.safetensors", "model.layers.35.shared_mlp.output_linear.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.10.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.10.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.10.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.10.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.10.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.11.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.11.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.11.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.11.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.11.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.12.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.12.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.12.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.12.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.12.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.13.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.13.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.13.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.13.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.13.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.14.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.14.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.14.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.14.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.14.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.15.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.15.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.15.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.15.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.15.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.16.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.16.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.16.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.16.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.16.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.17.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.17.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.17.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.17.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.17.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.18.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.18.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.18.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.18.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.18.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.19.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.19.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.19.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.19.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.19.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.20.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.20.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.20.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.20.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.20.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.21.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.21.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.21.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.21.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.21.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.22.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.22.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.22.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.22.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.22.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.23.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.23.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.23.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.23.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.23.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.24.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.24.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.24.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.24.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.24.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.25.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.25.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.25.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.25.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.25.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.26.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.26.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.26.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.26.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.26.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.27.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.27.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.27.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.27.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.27.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.28.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.28.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.28.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.28.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.28.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.29.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.29.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.29.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.29.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.29.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.30.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.30.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.30.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.30.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.30.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.31.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.31.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.31.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.31.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.31.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.32.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.32.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.32.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.32.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.32.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.33.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.33.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.33.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.33.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.33.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.34.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.34.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.34.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.34.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.34.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.35.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.35.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.35.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.35.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.35.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.36.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.36.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.36.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.36.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.36.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.37.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.37.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.37.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.37.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.37.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.38.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.38.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.38.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.38.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.38.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.39.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.39.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.39.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.39.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.39.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.4.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.4.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.4.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.4.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.4.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.40.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.40.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.40.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.40.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.40.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.41.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.41.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.41.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.41.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.41.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.42.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.42.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.42.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.42.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.42.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.43.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.43.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.43.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.43.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.43.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.44.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.44.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.44.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.44.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.44.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.45.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.45.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.45.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.45.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.45.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.46.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.46.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.46.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.46.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.46.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.47.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.47.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.47.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.47.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.47.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.48.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.48.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.48.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.48.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.48.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.49.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.49.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.49.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.49.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.49.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.5.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.5.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.5.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.5.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.5.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.50.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.50.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.50.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.50.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.50.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.51.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.51.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.51.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.51.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.51.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.52.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.52.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.52.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.52.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.52.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.53.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.53.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.53.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.53.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.53.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.54.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.54.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.54.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.54.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.55.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.55.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.56.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.56.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.57.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.57.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.58.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.58.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.59.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.59.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.6.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.6.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.6.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.6.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.6.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.60.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.60.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.60.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.60.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.60.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.61.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.61.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.61.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.61.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.61.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.62.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.62.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.62.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.62.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.62.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.63.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.63.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.63.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.63.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.63.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.64.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.64.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.64.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.64.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.64.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.65.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.65.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.65.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.65.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.65.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.66.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.66.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.66.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.66.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.66.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.67.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.67.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.67.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.67.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.67.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.68.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.68.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.68.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.68.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.68.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.69.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.69.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.69.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.69.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.69.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.7.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.7.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.7.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.7.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.7.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.70.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.70.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.70.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.70.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.70.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.71.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.71.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.71.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.71.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.71.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.8.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.8.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.8.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.8.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.8.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.9.down_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.9.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.9.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.9.up_proj.input_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.9.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.router.layer.weight": "model-00006-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.36.mamba.A_log": "model-00007-of-00007.safetensors", "model.layers.36.mamba.D": "model-00007-of-00007.safetensors", "model.layers.36.mamba.conv1d.bias": "model-00007-of-00007.safetensors", "model.layers.36.mamba.conv1d.weight": "model-00007-of-00007.safetensors", "model.layers.36.mamba.dt_bias": "model-00007-of-00007.safetensors", "model.layers.36.mamba.in_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.mamba.in_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.mamba.in_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.mamba.norm.weight": "model-00007-of-00007.safetensors", "model.layers.36.mamba.out_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.mamba.out_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.mamba.out_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.36.shared_mlp.input_linear.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.shared_mlp.input_linear.weight": "model-00007-of-00007.safetensors", "model.layers.36.shared_mlp.input_linear.weight_scale": "model-00007-of-00007.safetensors", "model.layers.36.shared_mlp.output_linear.input_scale": "model-00007-of-00007.safetensors", "model.layers.36.shared_mlp.output_linear.weight": "model-00007-of-00007.safetensors", "model.layers.36.shared_mlp.output_linear.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.10.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.10.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.10.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.10.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.10.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.11.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.11.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.11.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.11.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.11.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.12.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.12.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.12.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.12.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.12.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.13.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.13.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.13.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.13.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.13.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.14.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.14.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.14.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.14.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.14.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.15.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.15.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.15.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.15.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.15.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.16.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.16.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.16.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.16.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.16.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.17.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.17.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.17.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.17.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.17.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.18.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.18.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.18.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.18.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.18.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.19.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.19.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.19.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.19.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.19.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.20.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.20.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.20.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.20.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.20.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.21.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.21.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.21.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.21.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.21.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.22.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.22.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.22.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.22.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.22.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.23.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.23.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.23.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.23.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.23.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.24.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.24.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.24.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.24.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.24.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.25.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.25.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.25.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.25.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.25.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.26.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.26.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.26.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.26.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.26.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.27.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.27.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.27.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.27.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.27.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.28.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.28.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.28.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.28.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.28.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.29.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.29.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.29.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.29.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.29.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.30.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.30.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.30.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.30.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.30.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.31.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.31.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.31.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.31.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.31.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.32.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.32.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.32.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.32.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.32.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.33.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.33.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.33.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.33.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.33.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.34.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.34.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.34.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.34.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.34.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.35.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.35.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.35.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.35.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.35.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.36.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.36.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.36.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.36.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.36.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.37.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.37.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.37.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.37.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.37.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.38.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.38.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.38.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.38.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.38.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.39.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.39.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.39.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.39.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.39.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.4.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.4.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.4.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.4.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.4.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.40.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.40.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.40.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.40.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.40.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.41.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.41.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.41.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.41.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.41.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.42.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.42.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.42.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.42.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.42.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.43.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.43.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.43.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.43.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.43.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.44.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.44.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.44.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.44.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.44.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.45.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.45.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.45.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.45.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.45.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.46.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.46.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.46.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.46.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.46.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.47.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.47.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.47.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.47.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.47.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.48.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.48.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.48.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.48.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.48.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.49.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.49.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.49.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.49.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.49.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.5.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.5.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.5.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.5.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.5.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.50.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.50.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.50.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.50.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.50.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.51.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.51.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.51.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.51.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.51.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.52.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.52.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.52.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.52.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.52.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.53.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.53.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.53.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.53.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.53.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.54.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.54.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.54.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.54.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.54.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.55.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.55.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.55.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.55.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.55.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.56.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.56.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.56.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.56.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.56.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.57.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.57.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.57.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.57.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.57.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.58.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.58.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.58.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.58.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.58.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.59.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.59.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.59.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.59.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.59.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.6.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.6.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.6.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.6.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.6.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.60.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.60.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.60.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.60.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.60.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.61.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.61.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.61.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.61.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.61.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.62.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.62.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.62.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.62.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.62.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.63.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.63.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.63.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.63.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.63.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.64.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.64.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.64.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.64.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.64.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.65.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.65.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.65.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.65.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.65.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.66.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.66.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.66.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.66.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.66.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.67.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.67.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.67.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.67.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.67.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.68.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.68.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.68.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.68.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.68.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.69.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.69.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.69.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.69.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.69.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.7.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.7.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.7.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.7.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.7.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.70.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.70.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.70.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.70.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.70.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.71.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.71.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.71.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.71.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.71.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.8.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.8.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.8.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.8.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.8.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.9.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.9.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.9.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.9.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.9.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.router.layer.weight": "model-00007-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.37.mamba.A_log": "model-00007-of-00007.safetensors", "model.layers.37.mamba.D": "model-00007-of-00007.safetensors", "model.layers.37.mamba.conv1d.bias": "model-00007-of-00007.safetensors", "model.layers.37.mamba.conv1d.weight": "model-00007-of-00007.safetensors", "model.layers.37.mamba.dt_bias": "model-00007-of-00007.safetensors", "model.layers.37.mamba.in_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.mamba.in_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.mamba.in_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.mamba.norm.weight": "model-00007-of-00007.safetensors", "model.layers.37.mamba.out_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.mamba.out_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.mamba.out_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.37.shared_mlp.input_linear.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.shared_mlp.input_linear.weight": "model-00007-of-00007.safetensors", "model.layers.37.shared_mlp.input_linear.weight_scale": "model-00007-of-00007.safetensors", "model.layers.37.shared_mlp.output_linear.input_scale": "model-00007-of-00007.safetensors", "model.layers.37.shared_mlp.output_linear.weight": "model-00007-of-00007.safetensors", "model.layers.37.shared_mlp.output_linear.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.10.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.10.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.10.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.10.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.10.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.11.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.11.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.11.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.11.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.11.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.12.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.12.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.12.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.12.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.12.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.13.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.13.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.13.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.13.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.13.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.14.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.14.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.14.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.14.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.14.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.15.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.15.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.15.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.15.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.15.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.16.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.16.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.16.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.16.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.16.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.17.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.17.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.17.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.17.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.17.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.18.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.18.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.18.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.18.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.18.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.19.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.19.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.19.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.19.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.19.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.20.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.20.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.20.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.20.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.20.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.21.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.21.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.21.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.21.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.21.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.22.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.22.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.22.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.22.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.22.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.23.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.23.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.23.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.23.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.23.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.24.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.24.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.24.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.24.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.24.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.25.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.25.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.25.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.25.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.25.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.26.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.26.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.26.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.26.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.26.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.27.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.27.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.27.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.27.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.27.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.28.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.28.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.28.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.28.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.28.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.29.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.29.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.29.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.29.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.29.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.30.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.30.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.30.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.30.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.30.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.31.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.31.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.31.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.31.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.31.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.32.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.32.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.32.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.32.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.32.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.33.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.33.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.33.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.33.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.33.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.34.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.34.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.34.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.34.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.34.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.35.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.35.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.35.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.35.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.35.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.36.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.36.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.36.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.36.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.36.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.37.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.37.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.37.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.37.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.37.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.38.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.38.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.38.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.38.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.38.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.39.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.39.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.39.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.39.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.39.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.4.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.4.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.4.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.4.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.4.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.40.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.40.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.40.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.40.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.40.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.41.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.41.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.41.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.41.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.41.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.42.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.42.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.42.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.42.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.42.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.43.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.43.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.43.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.43.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.43.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.44.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.44.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.44.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.44.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.44.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.45.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.45.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.45.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.45.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.45.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.46.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.46.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.46.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.46.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.46.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.47.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.47.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.47.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.47.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.47.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.48.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.48.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.48.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.48.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.48.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.49.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.49.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.49.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.49.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.49.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.5.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.5.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.5.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.5.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.5.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.50.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.50.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.50.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.50.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.50.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.51.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.51.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.51.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.51.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.51.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.52.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.52.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.52.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.52.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.52.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.53.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.53.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.53.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.53.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.53.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.54.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.54.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.54.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.54.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.54.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.55.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.55.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.55.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.55.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.55.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.56.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.56.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.56.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.56.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.56.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.57.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.57.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.57.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.57.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.57.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.58.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.58.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.58.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.58.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.58.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.59.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.59.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.59.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.59.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.59.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.6.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.6.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.6.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.6.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.6.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.60.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.60.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.60.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.60.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.60.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.61.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.61.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.61.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.61.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.61.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.62.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.62.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.62.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.62.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.62.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.63.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.63.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.63.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.63.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.63.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.64.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.64.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.64.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.64.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.64.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.65.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.65.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.65.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.65.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.65.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.66.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.66.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.66.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.66.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.66.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.67.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.67.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.67.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.67.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.67.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.68.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.68.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.68.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.68.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.68.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.69.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.69.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.69.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.69.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.69.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.7.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.7.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.7.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.7.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.7.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.70.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.70.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.70.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.70.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.70.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.71.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.71.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.71.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.71.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.71.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.8.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.8.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.8.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.8.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.8.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.9.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.9.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.9.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.9.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.9.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.router.layer.weight": "model-00007-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.38.mamba.A_log": "model-00007-of-00007.safetensors", "model.layers.38.mamba.D": "model-00007-of-00007.safetensors", "model.layers.38.mamba.conv1d.bias": "model-00007-of-00007.safetensors", "model.layers.38.mamba.conv1d.weight": "model-00007-of-00007.safetensors", "model.layers.38.mamba.dt_bias": "model-00007-of-00007.safetensors", "model.layers.38.mamba.in_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.mamba.in_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.mamba.in_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.mamba.norm.weight": "model-00007-of-00007.safetensors", "model.layers.38.mamba.out_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.mamba.out_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.mamba.out_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.38.shared_mlp.input_linear.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.shared_mlp.input_linear.weight": "model-00007-of-00007.safetensors", "model.layers.38.shared_mlp.input_linear.weight_scale": "model-00007-of-00007.safetensors", "model.layers.38.shared_mlp.output_linear.input_scale": "model-00007-of-00007.safetensors", "model.layers.38.shared_mlp.output_linear.weight": "model-00007-of-00007.safetensors", "model.layers.38.shared_mlp.output_linear.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.10.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.10.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.10.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.10.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.10.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.11.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.11.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.11.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.11.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.11.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.12.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.12.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.12.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.12.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.12.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.13.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.13.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.13.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.13.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.13.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.14.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.14.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.14.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.14.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.14.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.15.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.15.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.15.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.15.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.15.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.16.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.16.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.16.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.16.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.16.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.17.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.17.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.17.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.17.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.17.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.18.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.18.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.18.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.18.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.18.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.19.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.19.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.19.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.19.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.19.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.20.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.20.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.20.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.20.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.20.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.21.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.21.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.21.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.21.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.21.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.22.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.22.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.22.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.22.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.22.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.23.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.23.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.23.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.23.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.23.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.24.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.24.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.24.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.24.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.24.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.25.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.25.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.25.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.25.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.25.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.26.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.26.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.26.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.26.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.26.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.27.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.27.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.27.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.27.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.27.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.28.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.28.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.28.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.28.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.28.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.29.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.29.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.29.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.29.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.29.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.30.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.30.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.30.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.30.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.30.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.31.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.31.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.31.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.31.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.31.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.32.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.32.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.32.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.32.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.32.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.33.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.33.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.33.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.33.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.33.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.34.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.34.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.34.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.34.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.34.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.35.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.35.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.35.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.35.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.35.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.36.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.36.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.36.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.36.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.36.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.37.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.37.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.37.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.37.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.37.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.38.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.38.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.38.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.38.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.38.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.39.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.39.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.39.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.39.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.39.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.4.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.4.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.4.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.4.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.4.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.40.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.40.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.40.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.40.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.40.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.41.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.41.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.41.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.41.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.41.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.42.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.42.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.42.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.42.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.42.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.43.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.43.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.43.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.43.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.43.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.44.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.44.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.44.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.44.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.44.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.45.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.45.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.45.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.45.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.45.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.46.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.46.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.46.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.46.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.46.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.47.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.47.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.47.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.47.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.47.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.48.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.48.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.48.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.48.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.48.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.49.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.49.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.49.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.49.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.49.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.5.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.5.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.5.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.5.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.5.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.50.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.50.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.50.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.50.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.50.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.51.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.51.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.51.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.51.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.51.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.52.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.52.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.52.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.52.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.52.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.53.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.53.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.53.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.53.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.53.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.54.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.54.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.54.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.54.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.54.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.55.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.55.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.55.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.55.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.55.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.56.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.56.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.56.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.56.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.56.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.57.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.57.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.57.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.57.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.57.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.58.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.58.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.58.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.58.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.58.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.59.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.59.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.59.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.59.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.59.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.6.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.6.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.6.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.6.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.6.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.60.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.60.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.60.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.60.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.60.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.61.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.61.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.61.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.61.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.61.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.62.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.62.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.62.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.62.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.62.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.63.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.63.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.63.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.63.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.63.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.64.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.64.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.64.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.64.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.64.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.65.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.65.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.65.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.65.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.65.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.66.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.66.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.66.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.66.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.66.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.67.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.67.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.67.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.67.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.67.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.68.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.68.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.68.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.68.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.68.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.69.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.69.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.69.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.69.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.69.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.7.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.7.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.7.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.7.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.7.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.70.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.70.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.70.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.70.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.70.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.71.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.71.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.71.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.71.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.71.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.8.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.8.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.8.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.8.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.8.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.9.down_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.9.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.9.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.9.up_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.9.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.router.layer.weight": "model-00007-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.39.mamba.A_log": "model-00007-of-00007.safetensors", "model.layers.39.mamba.D": "model-00007-of-00007.safetensors", "model.layers.39.mamba.conv1d.bias": "model-00007-of-00007.safetensors", "model.layers.39.mamba.conv1d.weight": "model-00007-of-00007.safetensors", "model.layers.39.mamba.dt_bias": "model-00007-of-00007.safetensors", "model.layers.39.mamba.in_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.mamba.in_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.mamba.in_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.mamba.norm.weight": "model-00007-of-00007.safetensors", "model.layers.39.mamba.out_proj.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.mamba.out_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.mamba.out_proj.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.39.shared_mlp.input_linear.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.shared_mlp.input_linear.weight": "model-00007-of-00007.safetensors", "model.layers.39.shared_mlp.input_linear.weight_scale": "model-00007-of-00007.safetensors", "model.layers.39.shared_mlp.output_linear.input_scale": "model-00007-of-00007.safetensors", "model.layers.39.shared_mlp.output_linear.weight": "model-00007-of-00007.safetensors", "model.layers.39.shared_mlp.output_linear.weight_scale": "model-00007-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.10.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.10.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.10.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.10.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.10.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.11.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.11.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.11.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.11.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.11.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.12.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.12.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.12.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.12.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.12.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.13.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.13.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.13.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.13.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.13.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.14.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.14.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.14.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.14.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.14.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.15.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.15.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.15.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.15.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.15.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.16.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.16.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.16.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.16.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.16.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.17.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.17.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.17.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.17.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.17.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.18.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.18.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.18.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.18.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.18.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.19.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.19.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.19.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.19.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.19.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.20.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.20.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.20.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.20.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.20.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.21.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.21.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.21.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.21.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.21.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.22.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.22.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.22.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.22.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.22.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.23.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.23.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.23.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.23.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.23.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.24.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.24.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.24.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.24.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.24.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.25.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.25.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.25.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.25.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.25.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.26.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.26.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.26.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.26.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.26.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.27.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.27.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.27.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.27.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.27.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.28.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.28.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.28.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.28.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.28.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.29.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.29.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.29.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.29.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.29.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.30.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.30.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.30.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.30.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.30.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.31.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.31.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.31.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.31.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.31.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.32.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.32.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.32.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.32.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.32.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.33.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.33.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.33.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.33.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.33.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.34.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.34.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.34.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.34.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.34.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.35.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.35.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.35.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.35.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.35.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.36.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.36.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.36.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.36.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.36.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.37.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.37.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.37.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.37.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.37.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.38.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.38.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.38.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.38.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.38.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.39.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.39.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.39.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.39.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.39.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.4.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.4.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.4.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.4.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.4.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.40.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.40.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.40.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.40.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.40.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.41.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.41.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.41.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.41.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.41.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.42.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.42.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.42.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.42.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.42.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.43.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.43.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.43.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.43.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.43.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.44.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.44.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.44.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.44.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.44.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.45.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.45.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.45.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.45.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.45.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.46.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.46.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.46.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.46.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.46.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.47.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.47.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.47.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.47.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.47.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.48.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.48.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.48.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.48.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.48.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.49.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.49.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.49.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.49.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.49.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.5.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.5.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.5.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.5.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.5.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.50.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.50.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.50.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.50.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.50.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.51.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.51.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.51.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.51.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.51.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.52.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.52.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.52.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.52.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.52.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.53.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.53.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.53.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.53.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.53.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.54.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.54.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.54.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.54.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.54.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.55.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.55.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.55.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.55.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.55.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.56.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.56.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.56.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.56.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.56.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.57.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.57.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.57.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.57.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.57.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.58.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.58.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.58.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.58.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.58.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.59.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.59.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.59.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.59.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.59.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.6.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.6.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.6.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.6.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.6.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.60.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.60.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.60.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.60.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.60.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.61.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.61.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.61.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.61.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.61.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.62.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.62.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.62.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.62.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.62.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.63.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.63.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.63.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.63.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.63.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.64.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.64.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.64.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.64.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.64.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.65.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.65.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.65.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.65.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.65.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.66.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.66.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.66.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.66.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.66.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.67.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.67.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.67.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.67.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.67.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.68.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.68.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.68.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.68.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.68.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.69.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.69.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.69.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.69.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.69.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.7.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.7.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.7.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.7.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.7.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.70.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.70.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.70.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.70.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.70.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.71.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.71.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.71.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.71.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.71.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.8.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.8.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.8.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.8.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.8.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.9.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.9.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.9.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.9.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.9.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.router.layer.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.mamba.A_log": "model-00001-of-00007.safetensors", "model.layers.4.mamba.D": "model-00001-of-00007.safetensors", "model.layers.4.mamba.conv1d.bias": "model-00001-of-00007.safetensors", "model.layers.4.mamba.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.4.mamba.dt_bias": "model-00001-of-00007.safetensors", "model.layers.4.mamba.in_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.mamba.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mamba.in_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.mamba.norm.weight": "model-00001-of-00007.safetensors", "model.layers.4.mamba.out_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.mamba.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mamba.out_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.shared_mlp.input_linear.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.shared_mlp.input_linear.weight": "model-00001-of-00007.safetensors", "model.layers.4.shared_mlp.input_linear.weight_scale": "model-00001-of-00007.safetensors", "model.layers.4.shared_mlp.output_linear.input_scale": "model-00001-of-00007.safetensors", "model.layers.4.shared_mlp.output_linear.weight": "model-00001-of-00007.safetensors", "model.layers.4.shared_mlp.output_linear.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.10.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.10.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.10.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.10.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.10.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.11.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.11.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.11.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.11.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.11.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.12.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.12.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.12.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.12.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.12.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.13.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.13.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.13.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.13.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.13.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.14.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.14.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.14.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.14.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.14.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.15.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.15.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.15.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.15.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.15.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.16.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.16.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.16.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.16.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.16.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.17.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.17.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.17.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.17.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.17.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.18.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.18.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.18.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.18.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.18.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.19.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.19.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.19.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.19.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.19.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.20.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.20.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.20.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.20.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.20.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.21.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.21.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.21.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.21.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.21.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.22.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.22.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.22.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.22.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.22.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.23.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.23.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.23.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.23.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.23.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.24.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.24.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.24.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.24.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.24.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.25.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.25.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.25.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.25.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.25.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.26.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.26.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.26.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.26.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.26.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.27.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.27.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.27.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.27.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.27.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.28.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.28.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.28.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.28.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.28.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.29.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.29.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.29.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.29.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.29.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.30.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.30.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.30.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.30.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.30.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.31.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.31.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.31.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.31.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.31.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.32.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.32.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.32.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.32.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.32.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.33.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.33.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.33.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.33.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.33.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.34.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.34.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.34.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.34.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.34.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.35.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.35.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.35.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.35.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.35.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.36.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.36.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.36.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.36.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.36.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.37.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.37.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.37.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.37.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.37.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.38.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.38.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.38.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.38.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.38.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.39.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.39.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.39.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.39.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.39.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.4.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.4.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.4.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.4.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.4.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.40.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.40.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.40.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.40.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.40.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.41.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.41.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.41.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.41.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.41.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.42.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.42.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.42.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.42.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.42.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.43.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.43.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.43.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.43.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.43.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.44.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.44.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.44.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.44.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.44.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.45.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.45.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.45.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.45.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.45.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.46.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.46.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.46.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.46.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.46.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.47.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.47.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.47.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.47.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.47.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.48.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.48.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.48.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.48.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.48.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.49.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.49.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.49.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.49.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.49.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.5.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.5.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.5.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.5.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.5.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.50.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.50.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.50.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.50.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.50.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.51.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.51.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.51.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.51.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.51.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.52.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.52.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.52.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.52.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.52.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.53.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.53.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.53.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.53.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.53.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.54.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.54.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.54.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.54.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.54.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.55.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.55.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.55.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.55.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.55.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.56.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.56.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.56.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.56.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.56.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.57.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.57.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.57.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.57.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.57.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.58.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.58.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.58.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.58.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.58.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.59.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.59.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.59.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.59.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.59.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.6.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.6.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.6.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.6.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.6.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.60.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.60.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.60.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.60.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.60.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.61.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.61.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.61.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.61.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.61.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.62.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.62.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.62.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.62.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.62.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.63.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.63.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.63.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.63.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.63.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.64.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.64.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.64.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.64.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.64.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.65.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.65.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.65.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.65.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.65.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.66.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.66.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.66.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.66.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.66.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.67.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.67.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.67.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.67.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.67.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.68.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.68.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.68.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.68.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.68.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.69.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.69.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.69.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.69.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.69.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.7.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.7.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.7.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.7.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.7.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.70.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.70.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.70.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.70.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.70.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.71.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.71.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.71.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.71.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.71.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.8.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.8.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.8.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.8.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.8.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.9.down_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.9.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.9.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.9.up_proj.input_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.9.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.router.layer.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.k_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.k_proj.output_scale": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.o_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.q_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.v_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.v_proj.output_scale": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.shared_mlp.input_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.shared_mlp.input_linear.weight": "model-00002-of-00007.safetensors", "model.layers.5.shared_mlp.input_linear.weight_scale": "model-00002-of-00007.safetensors", "model.layers.5.shared_mlp.output_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.5.shared_mlp.output_linear.weight": "model-00002-of-00007.safetensors", "model.layers.5.shared_mlp.output_linear.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.10.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.10.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.10.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.10.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.10.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.11.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.11.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.11.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.11.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.11.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.12.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.12.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.12.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.12.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.12.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.13.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.13.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.13.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.13.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.13.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.14.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.14.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.14.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.14.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.14.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.15.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.15.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.15.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.15.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.15.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.16.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.16.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.16.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.16.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.16.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.17.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.17.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.17.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.17.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.17.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.18.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.18.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.18.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.18.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.18.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.19.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.19.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.19.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.19.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.19.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.20.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.20.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.20.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.20.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.20.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.21.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.21.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.21.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.21.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.21.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.22.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.22.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.22.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.22.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.22.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.23.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.23.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.23.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.23.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.23.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.24.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.24.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.24.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.24.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.24.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.25.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.25.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.25.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.25.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.25.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.26.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.26.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.26.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.26.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.26.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.27.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.27.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.27.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.27.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.27.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.28.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.28.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.28.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.28.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.28.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.29.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.29.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.29.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.29.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.29.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.30.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.30.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.30.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.30.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.30.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.31.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.31.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.31.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.31.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.31.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.32.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.32.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.32.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.32.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.32.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.33.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.33.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.33.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.33.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.33.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.34.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.34.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.34.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.34.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.34.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.35.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.35.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.35.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.35.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.35.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.36.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.36.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.36.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.36.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.36.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.37.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.37.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.37.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.37.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.37.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.38.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.38.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.38.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.38.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.38.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.39.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.39.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.39.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.39.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.39.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.4.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.4.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.4.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.4.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.4.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.40.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.40.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.40.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.40.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.40.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.41.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.41.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.41.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.41.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.41.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.42.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.42.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.42.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.42.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.42.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.43.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.43.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.43.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.43.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.43.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.44.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.44.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.44.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.44.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.44.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.45.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.45.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.45.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.45.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.45.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.46.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.46.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.46.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.46.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.46.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.47.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.47.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.47.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.47.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.47.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.48.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.48.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.48.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.48.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.48.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.49.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.49.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.49.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.49.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.49.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.5.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.5.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.5.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.5.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.5.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.50.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.50.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.50.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.50.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.50.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.51.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.51.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.51.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.51.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.51.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.52.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.52.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.52.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.52.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.52.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.53.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.53.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.53.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.53.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.53.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.54.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.54.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.54.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.54.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.54.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.55.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.55.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.55.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.55.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.55.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.56.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.56.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.56.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.56.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.56.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.57.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.57.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.57.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.57.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.57.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.58.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.58.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.58.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.58.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.58.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.59.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.59.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.59.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.59.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.59.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.6.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.6.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.6.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.6.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.6.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.60.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.60.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.60.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.60.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.60.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.61.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.61.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.61.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.61.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.61.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.62.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.62.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.62.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.62.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.62.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.63.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.63.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.63.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.63.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.63.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.64.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.64.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.64.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.64.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.64.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.65.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.65.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.65.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.65.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.65.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.66.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.66.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.66.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.66.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.66.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.67.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.67.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.67.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.67.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.67.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.68.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.68.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.68.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.68.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.68.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.69.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.69.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.69.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.69.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.69.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.7.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.7.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.7.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.7.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.7.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.70.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.70.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.70.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.70.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.70.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.71.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.71.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.71.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.71.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.71.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.8.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.8.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.8.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.8.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.8.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.9.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.9.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.9.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.9.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.9.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.router.layer.weight": "model-00002-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.mamba.A_log": "model-00002-of-00007.safetensors", "model.layers.6.mamba.D": "model-00002-of-00007.safetensors", "model.layers.6.mamba.conv1d.bias": "model-00002-of-00007.safetensors", "model.layers.6.mamba.conv1d.weight": "model-00002-of-00007.safetensors", "model.layers.6.mamba.dt_bias": "model-00002-of-00007.safetensors", "model.layers.6.mamba.in_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.mamba.in_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mamba.in_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.mamba.norm.weight": "model-00002-of-00007.safetensors", "model.layers.6.mamba.out_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.mamba.out_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mamba.out_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.shared_mlp.input_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.shared_mlp.input_linear.weight": "model-00002-of-00007.safetensors", "model.layers.6.shared_mlp.input_linear.weight_scale": "model-00002-of-00007.safetensors", "model.layers.6.shared_mlp.output_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.6.shared_mlp.output_linear.weight": "model-00002-of-00007.safetensors", "model.layers.6.shared_mlp.output_linear.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.10.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.10.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.10.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.10.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.10.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.11.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.11.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.11.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.11.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.11.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.12.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.12.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.12.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.12.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.12.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.13.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.13.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.13.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.13.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.13.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.14.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.14.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.14.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.14.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.14.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.15.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.15.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.15.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.15.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.15.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.16.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.16.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.16.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.16.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.16.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.17.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.17.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.17.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.17.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.17.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.18.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.18.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.18.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.18.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.18.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.19.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.19.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.19.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.19.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.19.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.20.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.20.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.20.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.20.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.20.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.21.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.21.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.21.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.21.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.21.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.22.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.22.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.22.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.22.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.22.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.23.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.23.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.23.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.23.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.23.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.24.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.24.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.24.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.24.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.24.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.25.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.25.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.25.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.25.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.25.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.26.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.26.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.26.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.26.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.26.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.27.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.27.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.27.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.27.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.27.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.28.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.28.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.28.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.28.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.28.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.29.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.29.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.29.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.29.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.29.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.30.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.30.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.30.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.30.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.30.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.31.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.31.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.31.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.31.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.31.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.32.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.32.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.32.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.32.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.32.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.33.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.33.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.33.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.33.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.33.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.34.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.34.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.34.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.34.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.34.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.35.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.35.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.35.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.35.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.35.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.36.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.36.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.36.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.36.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.36.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.37.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.37.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.37.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.37.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.37.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.38.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.38.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.38.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.38.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.38.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.39.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.39.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.39.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.39.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.39.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.4.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.4.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.4.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.4.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.4.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.40.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.40.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.40.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.40.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.40.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.41.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.41.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.41.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.41.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.41.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.42.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.42.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.42.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.42.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.42.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.43.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.43.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.43.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.43.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.43.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.44.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.44.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.44.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.44.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.44.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.45.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.45.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.45.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.45.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.45.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.46.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.46.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.46.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.46.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.46.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.47.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.47.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.47.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.47.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.47.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.48.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.48.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.48.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.48.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.48.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.49.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.49.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.49.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.49.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.49.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.5.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.5.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.5.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.5.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.5.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.50.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.50.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.50.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.50.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.50.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.51.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.51.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.51.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.51.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.51.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.52.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.52.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.52.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.52.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.52.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.53.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.53.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.53.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.53.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.53.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.54.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.54.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.54.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.54.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.54.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.55.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.55.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.55.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.55.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.55.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.56.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.56.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.56.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.56.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.56.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.57.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.57.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.57.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.57.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.57.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.58.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.58.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.58.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.58.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.58.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.59.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.59.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.59.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.59.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.59.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.6.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.6.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.6.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.6.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.6.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.60.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.60.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.60.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.60.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.60.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.61.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.61.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.61.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.61.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.61.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.62.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.62.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.62.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.62.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.62.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.63.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.63.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.63.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.63.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.63.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.64.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.64.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.64.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.64.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.64.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.65.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.65.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.65.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.65.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.65.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.66.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.66.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.66.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.66.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.66.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.67.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.67.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.67.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.67.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.67.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.68.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.68.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.68.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.68.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.68.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.69.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.69.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.69.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.69.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.69.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.7.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.7.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.7.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.7.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.7.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.70.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.70.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.70.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.70.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.70.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.71.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.71.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.71.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.71.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.71.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.8.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.8.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.8.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.8.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.8.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.9.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.9.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.9.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.9.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.9.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.router.layer.weight": "model-00002-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.mamba.A_log": "model-00002-of-00007.safetensors", "model.layers.7.mamba.D": "model-00002-of-00007.safetensors", "model.layers.7.mamba.conv1d.bias": "model-00002-of-00007.safetensors", "model.layers.7.mamba.conv1d.weight": "model-00002-of-00007.safetensors", "model.layers.7.mamba.dt_bias": "model-00002-of-00007.safetensors", "model.layers.7.mamba.in_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.mamba.in_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mamba.in_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.mamba.norm.weight": "model-00002-of-00007.safetensors", "model.layers.7.mamba.out_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.mamba.out_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mamba.out_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.shared_mlp.input_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.shared_mlp.input_linear.weight": "model-00002-of-00007.safetensors", "model.layers.7.shared_mlp.input_linear.weight_scale": "model-00002-of-00007.safetensors", "model.layers.7.shared_mlp.output_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.7.shared_mlp.output_linear.weight": "model-00002-of-00007.safetensors", "model.layers.7.shared_mlp.output_linear.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.10.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.10.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.10.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.10.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.10.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.11.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.11.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.11.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.11.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.11.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.12.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.12.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.12.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.12.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.12.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.13.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.13.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.13.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.13.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.13.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.14.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.14.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.14.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.14.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.14.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.15.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.15.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.15.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.15.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.15.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.16.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.16.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.16.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.16.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.16.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.17.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.17.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.17.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.17.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.17.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.18.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.18.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.18.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.18.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.18.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.19.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.19.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.19.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.19.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.19.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.20.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.20.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.20.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.20.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.20.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.21.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.21.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.21.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.21.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.21.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.22.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.22.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.22.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.22.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.22.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.23.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.23.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.23.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.23.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.23.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.24.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.24.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.24.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.24.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.24.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.25.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.25.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.25.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.25.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.25.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.26.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.26.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.26.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.26.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.26.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.27.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.27.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.27.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.27.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.27.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.28.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.28.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.28.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.28.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.28.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.29.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.29.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.29.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.29.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.29.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.30.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.30.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.30.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.30.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.30.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.31.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.31.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.31.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.31.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.31.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.32.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.32.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.32.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.32.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.32.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.33.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.33.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.33.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.33.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.33.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.34.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.34.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.34.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.34.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.34.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.35.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.35.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.35.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.35.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.35.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.36.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.36.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.36.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.36.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.36.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.37.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.37.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.37.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.37.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.37.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.38.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.38.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.38.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.38.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.38.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.39.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.39.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.39.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.39.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.39.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.4.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.4.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.4.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.4.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.4.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.40.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.40.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.40.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.40.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.40.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.41.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.41.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.41.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.41.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.41.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.42.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.42.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.42.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.42.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.42.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.43.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.43.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.43.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.43.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.43.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.44.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.44.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.44.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.44.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.44.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.45.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.45.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.45.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.45.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.45.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.46.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.46.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.46.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.46.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.46.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.47.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.47.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.47.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.47.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.47.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.48.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.48.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.48.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.48.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.48.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.49.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.49.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.49.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.49.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.49.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.5.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.5.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.5.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.5.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.5.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.50.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.50.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.50.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.50.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.50.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.51.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.51.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.51.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.51.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.51.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.52.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.52.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.52.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.52.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.52.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.53.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.53.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.53.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.53.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.53.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.54.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.54.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.54.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.54.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.54.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.55.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.55.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.55.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.55.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.55.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.56.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.56.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.56.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.56.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.56.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.57.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.57.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.57.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.57.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.57.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.58.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.58.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.58.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.58.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.58.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.59.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.59.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.59.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.59.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.59.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.6.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.6.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.6.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.6.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.6.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.60.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.60.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.60.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.60.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.60.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.61.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.61.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.61.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.61.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.61.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.62.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.62.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.62.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.62.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.62.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.63.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.63.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.63.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.63.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.63.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.64.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.64.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.64.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.64.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.64.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.65.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.65.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.65.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.65.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.65.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.66.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.66.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.66.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.66.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.66.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.67.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.67.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.67.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.67.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.67.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.68.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.68.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.68.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.68.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.68.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.69.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.69.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.69.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.69.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.69.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.7.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.7.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.7.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.7.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.7.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.70.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.70.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.70.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.70.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.70.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.71.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.71.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.71.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.71.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.71.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.8.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.8.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.8.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.8.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.8.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.9.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.9.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.9.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.9.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.9.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.router.layer.weight": "model-00002-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.mamba.A_log": "model-00002-of-00007.safetensors", "model.layers.8.mamba.D": "model-00002-of-00007.safetensors", "model.layers.8.mamba.conv1d.bias": "model-00002-of-00007.safetensors", "model.layers.8.mamba.conv1d.weight": "model-00002-of-00007.safetensors", "model.layers.8.mamba.dt_bias": "model-00002-of-00007.safetensors", "model.layers.8.mamba.in_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.mamba.in_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mamba.in_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.mamba.norm.weight": "model-00002-of-00007.safetensors", "model.layers.8.mamba.out_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.mamba.out_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mamba.out_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.shared_mlp.input_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.shared_mlp.input_linear.weight": "model-00002-of-00007.safetensors", "model.layers.8.shared_mlp.input_linear.weight_scale": "model-00002-of-00007.safetensors", "model.layers.8.shared_mlp.output_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.8.shared_mlp.output_linear.weight": "model-00002-of-00007.safetensors", "model.layers.8.shared_mlp.output_linear.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.10.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.10.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.10.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.10.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.10.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.10.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.10.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.10.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.10.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.11.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.11.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.11.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.11.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.11.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.11.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.11.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.11.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.11.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.12.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.12.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.12.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.12.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.12.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.12.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.12.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.12.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.12.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.13.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.13.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.13.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.13.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.13.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.13.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.13.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.13.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.13.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.14.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.14.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.14.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.14.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.14.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.14.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.14.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.14.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.14.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.15.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.15.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.15.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.15.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.15.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.15.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.15.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.15.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.15.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.16.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.16.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.16.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.16.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.16.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.16.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.16.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.16.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.16.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.17.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.17.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.17.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.17.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.17.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.17.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.17.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.17.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.17.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.18.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.18.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.18.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.18.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.18.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.18.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.18.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.18.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.18.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.19.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.19.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.19.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.19.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.19.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.19.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.19.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.19.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.19.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.20.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.20.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.20.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.20.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.20.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.20.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.20.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.20.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.20.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.21.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.21.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.21.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.21.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.21.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.21.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.21.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.21.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.21.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.22.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.22.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.22.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.22.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.22.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.22.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.22.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.22.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.22.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.23.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.23.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.23.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.23.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.23.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.23.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.23.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.23.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.23.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.24.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.24.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.24.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.24.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.24.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.24.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.24.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.24.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.24.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.25.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.25.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.25.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.25.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.25.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.25.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.25.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.25.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.25.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.26.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.26.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.26.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.26.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.26.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.26.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.26.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.26.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.26.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.27.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.27.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.27.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.27.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.27.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.27.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.27.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.27.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.27.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.28.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.28.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.28.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.28.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.28.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.28.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.28.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.28.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.28.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.29.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.29.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.29.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.29.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.29.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.29.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.29.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.29.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.29.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.30.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.30.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.30.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.30.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.30.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.30.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.30.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.30.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.30.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.31.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.31.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.31.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.31.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.31.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.31.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.31.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.31.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.31.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.32.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.32.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.32.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.32.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.32.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.32.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.32.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.32.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.32.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.33.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.33.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.33.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.33.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.33.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.33.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.33.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.33.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.33.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.34.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.34.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.34.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.34.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.34.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.34.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.34.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.34.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.34.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.35.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.35.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.35.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.35.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.35.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.35.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.35.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.35.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.35.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.36.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.36.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.36.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.36.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.36.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.36.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.36.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.36.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.36.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.37.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.37.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.37.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.37.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.37.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.37.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.37.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.37.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.37.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.38.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.38.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.38.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.38.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.38.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.38.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.38.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.38.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.38.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.39.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.39.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.39.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.39.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.39.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.39.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.39.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.39.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.39.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.4.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.4.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.4.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.4.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.4.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.4.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.4.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.4.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.4.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.40.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.40.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.40.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.40.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.40.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.40.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.40.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.40.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.40.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.41.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.41.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.41.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.41.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.41.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.41.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.41.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.41.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.41.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.42.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.42.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.42.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.42.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.42.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.42.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.42.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.42.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.42.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.43.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.43.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.43.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.43.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.43.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.43.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.43.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.43.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.43.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.44.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.44.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.44.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.44.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.44.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.44.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.44.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.44.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.44.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.45.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.45.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.45.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.45.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.45.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.45.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.45.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.45.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.45.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.46.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.46.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.46.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.46.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.46.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.46.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.46.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.46.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.46.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.47.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.47.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.47.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.47.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.47.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.47.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.47.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.47.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.47.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.48.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.48.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.48.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.48.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.48.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.48.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.48.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.48.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.48.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.49.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.49.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.49.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.49.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.49.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.49.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.49.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.49.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.49.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.5.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.5.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.5.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.5.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.5.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.5.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.5.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.5.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.5.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.50.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.50.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.50.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.50.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.50.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.50.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.50.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.50.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.50.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.51.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.51.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.51.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.51.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.51.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.51.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.51.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.51.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.51.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.52.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.52.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.52.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.52.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.52.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.52.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.52.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.52.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.52.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.53.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.53.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.53.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.53.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.53.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.53.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.53.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.53.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.53.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.54.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.54.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.54.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.54.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.54.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.54.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.54.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.54.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.54.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.55.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.55.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.55.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.55.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.55.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.55.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.55.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.55.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.55.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.56.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.56.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.56.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.56.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.56.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.56.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.56.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.56.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.56.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.57.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.57.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.57.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.57.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.57.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.57.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.57.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.57.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.57.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.58.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.58.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.58.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.58.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.58.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.58.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.58.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.58.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.58.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.59.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.59.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.59.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.59.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.59.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.59.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.59.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.59.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.59.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.6.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.6.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.6.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.6.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.6.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.6.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.6.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.6.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.6.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.60.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.60.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.60.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.60.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.60.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.60.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.60.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.60.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.60.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.61.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.61.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.61.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.61.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.61.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.61.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.61.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.61.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.61.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.62.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.62.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.62.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.62.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.62.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.62.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.62.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.62.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.62.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.63.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.63.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.63.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.63.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.63.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.63.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.63.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.63.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.63.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.64.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.64.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.64.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.64.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.64.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.64.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.64.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.64.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.64.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.65.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.65.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.65.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.65.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.65.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.65.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.65.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.65.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.65.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.66.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.66.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.66.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.66.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.66.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.66.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.66.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.66.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.66.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.67.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.67.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.67.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.67.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.67.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.67.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.67.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.67.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.67.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.68.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.68.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.68.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.68.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.68.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.68.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.68.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.68.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.68.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.69.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.69.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.69.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.69.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.69.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.69.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.69.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.69.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.69.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.7.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.7.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.7.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.7.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.7.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.7.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.7.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.7.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.7.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.70.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.70.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.70.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.70.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.70.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.70.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.70.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.70.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.70.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.71.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.71.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.71.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.71.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.71.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.71.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.71.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.71.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.71.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.8.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.8.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.8.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.8.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.8.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.8.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.8.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.8.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.8.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.9.down_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.9.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.9.down_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.9.gate_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.9.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.9.gate_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.9.up_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.9.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.9.up_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.router.layer.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.mamba.A_log": "model-00002-of-00007.safetensors", "model.layers.9.mamba.D": "model-00002-of-00007.safetensors", "model.layers.9.mamba.conv1d.bias": "model-00002-of-00007.safetensors", "model.layers.9.mamba.conv1d.weight": "model-00002-of-00007.safetensors", "model.layers.9.mamba.dt_bias": "model-00002-of-00007.safetensors", "model.layers.9.mamba.in_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.mamba.in_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mamba.in_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.mamba.norm.weight": "model-00002-of-00007.safetensors", "model.layers.9.mamba.out_proj.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.mamba.out_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mamba.out_proj.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.shared_mlp.input_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.shared_mlp.input_linear.weight": "model-00002-of-00007.safetensors", "model.layers.9.shared_mlp.input_linear.weight_scale": "model-00002-of-00007.safetensors", "model.layers.9.shared_mlp.output_linear.input_scale": "model-00002-of-00007.safetensors", "model.layers.9.shared_mlp.output_linear.weight": "model-00002-of-00007.safetensors", "model.layers.9.shared_mlp.output_linear.weight_scale": "model-00002-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors" } }