Download adapter_config.json from MLA299/Test-SMALL-Model: direct link, hf CLI and curl.
- Browser
- Download file 61 kB
-
https://huggingface.co/MLA299/Test-SMALL-Model/resolve/main/adapter_config.json
- Command line
-
hf download hf://MLA299/Test-SMALL-Model/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/MLA299/Test-SMALL-Model/resolve/main/adapter_config.json
61 kB
| { | |
| "fine_tune_type": "lora", | |
| "peft_type": "LORA", | |
| "base_model_name_or_path": "unsloth/Qwen3.5-2B", | |
| "learning_rate": 0.0002, | |
| "max_steps": 4, | |
| "max_seq_length": 2048, | |
| "use_cce": true, | |
| "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" | |
| } | |
| }, | |
| "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", | |
| "num_layers": 24, | |
| "lora_parameters": { | |
| "rank": 16, | |
| "scale": 4.0, | |
| "dropout": 0.0, | |
| "keys": [ | |
| "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" | |
| ] | |
| }, | |
| "rank": 16, | |
| "scale": 4.0, | |
| "dropout": 0.0, | |
| "base_model_commit_hash": "fffbc0d8711cf87df6d1f97938c5e50ef94aadc7", | |
| "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" | |
| } | |
| }, | |
| "requires_unsloth_mlx_runtime_quantization": true, | |
| "unsloth_mlx_lora_module_paths": [ | |
| "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" | |
| ] | |
| } |