| { |
| "metadata": { |
| "total_size": 33268506624 |
| }, |
| "weight_map": { |
| "language_model.model.embed_tokens.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.embed_tokens.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.embed_tokens.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.mlp.down_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.mlp.down_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.mlp.gate_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.mlp.gate_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.mlp.up_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.mlp.up_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.mlp.gate.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.mlp.gate.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.mlp.gate.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.mlp.gate.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.mlp.gate.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.mlp.gate.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.15.mlp.gate.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.mlp.gate.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.mlp.gate.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.mlp.gate.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.mlp.gate.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.mlp.gate.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.mlp.gate.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.mlp.gate.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.mlp.gate.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.23.mlp.gate.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", |
| "language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.mlp.gate.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.mlp.gate.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.mlp.gate.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.mlp.gate.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.mlp.gate.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.mlp.gate.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.mlp.gate.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.30.mlp.gate.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", |
| "language_model.model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.mlp.gate.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.mlp.gate.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.mlp.gate.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.mlp.gate.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.mlp.gate.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.mlp.gate.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.mlp.gate.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.38.input_layernorm.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.38.mlp.gate.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", |
| "language_model.model.layers.39.input_layernorm.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.mlp.gate.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.39.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.mlp.gate.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.40.input_layernorm.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.mlp.gate.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.40.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.input_layernorm.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.mlp.gate.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.41.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.mlp.gate.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.42.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.mlp.gate.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.mlp.gate.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.mlp.gate.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.46.input_layernorm.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.46.mlp.gate.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.46.mlp.switch_mlp.down_proj.biases": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.46.mlp.switch_mlp.down_proj.scales": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.46.mlp.switch_mlp.down_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.46.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.46.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.46.mlp.switch_mlp.up_proj.biases": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.46.mlp.switch_mlp.up_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", |
| "language_model.model.layers.47.input_layernorm.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.mlp.gate.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.mlp.switch_mlp.down_proj.biases": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.mlp.switch_mlp.down_proj.scales": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.mlp.switch_mlp.down_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.mlp.switch_mlp.up_proj.biases": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.mlp.switch_mlp.up_proj.scales": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.mlp.switch_mlp.up_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.47.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.input_layernorm.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.mlp.gate.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.mlp.switch_mlp.down_proj.biases": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.mlp.switch_mlp.down_proj.scales": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.mlp.switch_mlp.down_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.mlp.switch_mlp.up_proj.biases": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.mlp.switch_mlp.up_proj.scales": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.mlp.switch_mlp.up_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.48.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", |
| "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.mlp.gate.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.mlp.gate.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.7.mlp.gate.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", |
| "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.mlp.gate.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.mlp.gate.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", |
| "language_model.model.norm.weight": "model-00007-of-00007.safetensors" |
| } |
| } |
