| { |
| "base_model_name_or_path": "unsloth/Qwen3.5-4B", |
| "base_model_revision": "b85e62a1372ca32d6a37c81bccf70ad2cf8f779e", |
| "base_model_commit_hash": "b85e62a1372ca32d6a37c81bccf70ad2cf8f779e", |
| "base_quantization_config": { |
| "language_model.model.layers.0.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_qkv": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_z": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_b": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_a": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.linear_attn.out_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| } |
| }, |
| "base_quantization_policy": { |
| "enabled": true, |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine", |
| "source": "load_in_4bit", |
| "quantize_modules": null, |
| "has_callable_predicate": false, |
| "force_requantize": false |
| }, |
| "base_quantized_source": "runtime", |
| "base_resolved_quantization_map": { |
| "language_model.model.layers.0.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.0.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.1.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.2.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.self_attn.v_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.3.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.4.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.5.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.6.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.self_attn.v_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.7.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.8.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.9.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.10.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.self_attn.v_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.11.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.12.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.13.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.14.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.self_attn.v_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.15.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.16.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.17.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.18.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.self_attn.v_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.19.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.20.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.21.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.22.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.self_attn.v_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.23.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.24.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.25.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.26.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.self_attn.v_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.27.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.28.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.29.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_qkv": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.linear_attn.out_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.30.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.self_attn.v_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "language_model.model.layers.31.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| } |
| }, |
| "requires_unsloth_mlx_runtime_quantization": true, |
| "unsloth_mlx_lora_module_paths": [ |
| "language_model.model.layers.31.mlp.up_proj", |
| "language_model.model.layers.31.mlp.down_proj", |
| "language_model.model.layers.31.mlp.gate_proj", |
| "language_model.model.layers.31.self_attn.o_proj", |
| "language_model.model.layers.31.self_attn.v_proj", |
| "language_model.model.layers.31.self_attn.k_proj", |
| "language_model.model.layers.31.self_attn.q_proj", |
| "language_model.model.layers.30.mlp.up_proj", |
| "language_model.model.layers.30.mlp.down_proj", |
| "language_model.model.layers.30.mlp.gate_proj", |
| "language_model.model.layers.30.linear_attn.out_proj", |
| "language_model.model.layers.29.mlp.up_proj", |
| "language_model.model.layers.29.mlp.down_proj", |
| "language_model.model.layers.29.mlp.gate_proj", |
| "language_model.model.layers.29.linear_attn.out_proj", |
| "language_model.model.layers.28.mlp.up_proj", |
| "language_model.model.layers.28.mlp.down_proj", |
| "language_model.model.layers.28.mlp.gate_proj", |
| "language_model.model.layers.28.linear_attn.out_proj", |
| "language_model.model.layers.27.mlp.up_proj", |
| "language_model.model.layers.27.mlp.down_proj", |
| "language_model.model.layers.27.mlp.gate_proj", |
| "language_model.model.layers.27.self_attn.o_proj", |
| "language_model.model.layers.27.self_attn.v_proj", |
| "language_model.model.layers.27.self_attn.k_proj", |
| "language_model.model.layers.27.self_attn.q_proj", |
| "language_model.model.layers.26.mlp.up_proj", |
| "language_model.model.layers.26.mlp.down_proj", |
| "language_model.model.layers.26.mlp.gate_proj", |
| "language_model.model.layers.26.linear_attn.out_proj", |
| "language_model.model.layers.25.mlp.up_proj", |
| "language_model.model.layers.25.mlp.down_proj", |
| "language_model.model.layers.25.mlp.gate_proj", |
| "language_model.model.layers.25.linear_attn.out_proj", |
| "language_model.model.layers.24.mlp.up_proj", |
| "language_model.model.layers.24.mlp.down_proj", |
| "language_model.model.layers.24.mlp.gate_proj", |
| "language_model.model.layers.24.linear_attn.out_proj", |
| "language_model.model.layers.23.mlp.up_proj", |
| "language_model.model.layers.23.mlp.down_proj", |
| "language_model.model.layers.23.mlp.gate_proj", |
| "language_model.model.layers.23.self_attn.o_proj", |
| "language_model.model.layers.23.self_attn.v_proj", |
| "language_model.model.layers.23.self_attn.k_proj", |
| "language_model.model.layers.23.self_attn.q_proj", |
| "language_model.model.layers.22.mlp.up_proj", |
| "language_model.model.layers.22.mlp.down_proj", |
| "language_model.model.layers.22.mlp.gate_proj", |
| "language_model.model.layers.22.linear_attn.out_proj", |
| "language_model.model.layers.21.mlp.up_proj", |
| "language_model.model.layers.21.mlp.down_proj", |
| "language_model.model.layers.21.mlp.gate_proj", |
| "language_model.model.layers.21.linear_attn.out_proj", |
| "language_model.model.layers.20.mlp.up_proj", |
| "language_model.model.layers.20.mlp.down_proj", |
| "language_model.model.layers.20.mlp.gate_proj", |
| "language_model.model.layers.20.linear_attn.out_proj", |
| "language_model.model.layers.19.mlp.up_proj", |
| "language_model.model.layers.19.mlp.down_proj", |
| "language_model.model.layers.19.mlp.gate_proj", |
| "language_model.model.layers.19.self_attn.o_proj", |
| "language_model.model.layers.19.self_attn.v_proj", |
| "language_model.model.layers.19.self_attn.k_proj", |
| "language_model.model.layers.19.self_attn.q_proj", |
| "language_model.model.layers.18.mlp.up_proj", |
| "language_model.model.layers.18.mlp.down_proj", |
| "language_model.model.layers.18.mlp.gate_proj", |
| "language_model.model.layers.18.linear_attn.out_proj", |
| "language_model.model.layers.17.mlp.up_proj", |
| "language_model.model.layers.17.mlp.down_proj", |
| "language_model.model.layers.17.mlp.gate_proj", |
| "language_model.model.layers.17.linear_attn.out_proj", |
| "language_model.model.layers.16.mlp.up_proj", |
| "language_model.model.layers.16.mlp.down_proj", |
| "language_model.model.layers.16.mlp.gate_proj", |
| "language_model.model.layers.16.linear_attn.out_proj", |
| "language_model.model.layers.15.mlp.up_proj", |
| "language_model.model.layers.15.mlp.down_proj", |
| "language_model.model.layers.15.mlp.gate_proj", |
| "language_model.model.layers.15.self_attn.o_proj", |
| "language_model.model.layers.15.self_attn.v_proj", |
| "language_model.model.layers.15.self_attn.k_proj", |
| "language_model.model.layers.15.self_attn.q_proj", |
| "language_model.model.layers.14.mlp.up_proj", |
| "language_model.model.layers.14.mlp.down_proj", |
| "language_model.model.layers.14.mlp.gate_proj", |
| "language_model.model.layers.14.linear_attn.out_proj", |
| "language_model.model.layers.13.mlp.up_proj", |
| "language_model.model.layers.13.mlp.down_proj", |
| "language_model.model.layers.13.mlp.gate_proj", |
| "language_model.model.layers.13.linear_attn.out_proj", |
| "language_model.model.layers.12.mlp.up_proj", |
| "language_model.model.layers.12.mlp.down_proj", |
| "language_model.model.layers.12.mlp.gate_proj", |
| "language_model.model.layers.12.linear_attn.out_proj", |
| "language_model.model.layers.11.mlp.up_proj", |
| "language_model.model.layers.11.mlp.down_proj", |
| "language_model.model.layers.11.mlp.gate_proj", |
| "language_model.model.layers.11.self_attn.o_proj", |
| "language_model.model.layers.11.self_attn.v_proj", |
| "language_model.model.layers.11.self_attn.k_proj", |
| "language_model.model.layers.11.self_attn.q_proj", |
| "language_model.model.layers.10.mlp.up_proj", |
| "language_model.model.layers.10.mlp.down_proj", |
| "language_model.model.layers.10.mlp.gate_proj", |
| "language_model.model.layers.10.linear_attn.out_proj", |
| "language_model.model.layers.9.mlp.up_proj", |
| "language_model.model.layers.9.mlp.down_proj", |
| "language_model.model.layers.9.mlp.gate_proj", |
| "language_model.model.layers.9.linear_attn.out_proj", |
| "language_model.model.layers.8.mlp.up_proj", |
| "language_model.model.layers.8.mlp.down_proj", |
| "language_model.model.layers.8.mlp.gate_proj", |
| "language_model.model.layers.8.linear_attn.out_proj", |
| "language_model.model.layers.7.mlp.up_proj", |
| "language_model.model.layers.7.mlp.down_proj", |
| "language_model.model.layers.7.mlp.gate_proj", |
| "language_model.model.layers.7.self_attn.o_proj", |
| "language_model.model.layers.7.self_attn.v_proj", |
| "language_model.model.layers.7.self_attn.k_proj", |
| "language_model.model.layers.7.self_attn.q_proj", |
| "language_model.model.layers.6.mlp.up_proj", |
| "language_model.model.layers.6.mlp.down_proj", |
| "language_model.model.layers.6.mlp.gate_proj", |
| "language_model.model.layers.6.linear_attn.out_proj", |
| "language_model.model.layers.5.mlp.up_proj", |
| "language_model.model.layers.5.mlp.down_proj", |
| "language_model.model.layers.5.mlp.gate_proj", |
| "language_model.model.layers.5.linear_attn.out_proj", |
| "language_model.model.layers.4.mlp.up_proj", |
| "language_model.model.layers.4.mlp.down_proj", |
| "language_model.model.layers.4.mlp.gate_proj", |
| "language_model.model.layers.4.linear_attn.out_proj", |
| "language_model.model.layers.3.mlp.up_proj", |
| "language_model.model.layers.3.mlp.down_proj", |
| "language_model.model.layers.3.mlp.gate_proj", |
| "language_model.model.layers.3.self_attn.o_proj", |
| "language_model.model.layers.3.self_attn.v_proj", |
| "language_model.model.layers.3.self_attn.k_proj", |
| "language_model.model.layers.3.self_attn.q_proj", |
| "language_model.model.layers.2.mlp.up_proj", |
| "language_model.model.layers.2.mlp.down_proj", |
| "language_model.model.layers.2.mlp.gate_proj", |
| "language_model.model.layers.2.linear_attn.out_proj", |
| "language_model.model.layers.1.mlp.up_proj", |
| "language_model.model.layers.1.mlp.down_proj", |
| "language_model.model.layers.1.mlp.gate_proj", |
| "language_model.model.layers.1.linear_attn.out_proj", |
| "language_model.model.layers.0.mlp.up_proj", |
| "language_model.model.layers.0.mlp.down_proj", |
| "language_model.model.layers.0.mlp.gate_proj", |
| "language_model.model.layers.0.linear_attn.out_proj" |
| ] |
| } |