{ "bits": 4, "data_type": "int", "group_size": 128, "sym": true, "batch_size": 16, "gradient_accumulate_steps": 2, "low_gpu_mem_usage": true, "nsamples": 640, "autoround_version": "0.13.1", "block_name_to_quantize": "model.language_model.layers", "quant_method": "auto-round", "packing_format": "auto_round:auto_gptq", "extra_config": { "model.language_model.layers.0.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.1.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.2.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.3.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.4.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.5.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.6.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.7.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.8.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.9.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.10.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.11.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.12.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.13.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.14.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.15.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.16.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.17.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.18.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.19.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.20.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.21.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.22.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.23.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.24.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.25.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.26.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.27.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.28.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.29.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.30.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.31.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.32.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.33.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.34.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.35.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.36.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.37.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.38.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.39.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.40.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.41.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.42.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.43.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.44.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.45.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.46.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.47.mlp.shared_expert_gate": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.0.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.0.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.0.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.0.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.0.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.1.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.1.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.1.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.1.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.1.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.2.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.2.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.2.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.2.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.2.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.3.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.3.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.3.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.3.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.4.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.4.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.4.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.4.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.4.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.5.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.5.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.5.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.5.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.5.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.6.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.6.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.6.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.6.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.6.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.7.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.7.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.7.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.7.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.8.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.8.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.8.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.8.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.8.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.9.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.9.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.9.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.9.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.9.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.10.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.10.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.10.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.10.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.10.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.11.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.11.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.11.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.11.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.12.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.12.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.12.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.12.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.12.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.13.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.13.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.13.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.13.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.13.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.14.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.14.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.14.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.14.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.14.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.15.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.15.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.15.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.15.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.16.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.16.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.16.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.16.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.16.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.17.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.17.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.17.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.17.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.17.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.18.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.18.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.18.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.18.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.18.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.19.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.19.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.19.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.19.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.20.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.20.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.20.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.20.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.20.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.21.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.21.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.21.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.21.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.21.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.22.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.22.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.22.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.22.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.22.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.23.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.23.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.23.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.23.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.24.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.24.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.24.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.24.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.24.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.25.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.25.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.25.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.25.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.25.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.26.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.26.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.26.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.26.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.26.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.27.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.27.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.27.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.27.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.28.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.28.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.28.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.28.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.28.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.29.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.29.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.29.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.29.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.29.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.30.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.30.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.30.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.30.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.30.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.31.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.31.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.31.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.31.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.32.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.32.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.32.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.32.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.32.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.33.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.33.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.33.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.33.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.33.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.34.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.34.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.34.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.34.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.34.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.35.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.35.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.35.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.35.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.36.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.36.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.36.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.36.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.36.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.37.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.37.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.37.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.37.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.37.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.38.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.38.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.38.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.38.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.38.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.39.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.39.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.39.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.39.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.40.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.40.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.40.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.40.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.40.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.41.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.41.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.41.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.41.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.41.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.42.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.42.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.42.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.42.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.42.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.43.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.43.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.43.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.43.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.44.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.44.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.44.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.44.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.44.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.45.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.45.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.45.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.45.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.45.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.46.linear_attn.out_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.46.linear_attn.in_proj_qkv": { "bits": 16, "data_type": "float" }, "model.language_model.layers.46.linear_attn.in_proj_z": { "bits": 16, "data_type": "float" }, "model.language_model.layers.46.linear_attn.in_proj_b": { "bits": 16, "data_type": "float" }, "model.language_model.layers.46.linear_attn.in_proj_a": { "bits": 16, "data_type": "float" }, "model.language_model.layers.47.self_attn.q_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.47.self_attn.k_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.47.self_attn.v_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.47.self_attn.o_proj": { "bits": 16, "data_type": "float" }, "model.language_model.layers.0.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.0.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.0.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.1.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.1.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.1.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.2.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.2.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.2.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.3.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.3.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.3.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.4.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.4.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.4.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.5.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.5.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.5.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.6.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.6.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.6.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.7.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.7.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.7.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.8.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.8.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.8.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.9.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.9.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.9.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.10.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.10.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.10.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.11.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.11.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.11.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.12.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.12.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.12.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.13.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.13.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.13.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.14.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.14.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.14.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.15.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.15.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.15.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.16.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.16.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.16.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.17.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.17.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.17.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.18.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.18.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.18.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.19.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.19.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.19.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.20.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.20.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.20.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.21.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.21.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.21.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.22.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.22.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.22.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.23.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.23.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.23.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.24.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.24.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.24.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.25.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.25.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.25.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.26.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.26.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.26.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.27.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.27.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.27.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.28.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.28.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.28.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.29.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.29.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.29.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.30.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.30.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.30.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.31.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.31.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.31.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.32.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.32.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.32.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.33.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.33.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.33.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.34.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.34.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.34.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.35.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.35.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.35.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.36.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.36.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.36.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.37.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.37.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.37.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.38.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.38.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.38.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.39.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.39.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.39.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.40.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.40.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.40.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.41.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.41.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.41.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.42.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.42.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.42.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.43.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.43.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.43.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.44.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.44.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.44.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.45.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.45.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.45.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.46.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.46.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.46.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.47.mlp.shared_expert.gate_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.47.mlp.shared_expert.up_proj": { "bits": 16, "data_type": "fp" }, "model.language_model.layers.47.mlp.shared_expert.down_proj": { "bits": 16, "data_type": "fp" }, ".*attn.*": { "bits": 16, "data_type": "float" }, ".*shared_expert.*": { "bits": 16, "data_type": "fp" }, ".*shared_experts.*": { "bits": 16, "data_type": "float" }, ".*mtp.*": { "bits": 16, "data_type": "float" }, ".*visual.*": { "bits": 16, "data_type": "fp" }, ".*vision.*": { "bits": 16, "data_type": "float" }, ".*model\\.language_model\\.layers\\.[0-47]\\.mlp\\.gate.*": { "bits": 16, "data_type": "float" } } }