| { |
| "base_model_name_or_path": "microsoft/Phi-4-mini-reasoning", |
| "base_model_revision": "0e3b1e2d02ee478a3743abe3f629e9c0cb722e0a", |
| "base_model_commit_hash": "0e3b1e2d02ee478a3743abe3f629e9c0cb722e0a", |
| "base_quantization_config": { |
| "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": { |
| "model.layers.0.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.2.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.2.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.2.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.2.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.3.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.3.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.3.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.3.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.4.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.4.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.4.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.4.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.5.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.5.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.5.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.5.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.6.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.6.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.6.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.6.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.7.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.7.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.7.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.7.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.8.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.8.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.8.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.8.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.9.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.9.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.9.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.9.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.10.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.10.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.10.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.10.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.11.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.11.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.11.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.11.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.12.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.12.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.12.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.12.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.13.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.13.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.13.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.13.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.14.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.14.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.14.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.14.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.15.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.15.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.15.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.15.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.16.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.16.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.16.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.16.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.17.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.17.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.17.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.17.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.18.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.18.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.18.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.18.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.19.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.19.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.19.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.19.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.20.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.20.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.20.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.20.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.21.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.21.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.21.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.21.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.22.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.22.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.22.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.22.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.23.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.23.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.23.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.23.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.24.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.24.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.24.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.24.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.25.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.25.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.25.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.25.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.26.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.26.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.26.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.26.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.27.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.27.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.27.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.27.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.28.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.28.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.28.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.28.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.29.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.29.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.29.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.29.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.30.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.30.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.30.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.30.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.31.self_attn.qkv_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.31.self_attn.o_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.31.mlp.gate_up_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.31.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64, |
| "mode": "affine" |
| } |
| }, |
| "requires_unsloth_mlx_runtime_quantization": true, |
| "lora_parameters": { |
| "rank": 16, |
| "scale": 1.0, |
| "dropout": 0.0, |
| "keys": [ |
| "model.layers.31.mlp.down_proj", |
| "model.layers.31.mlp.gate_up_proj", |
| "model.layers.31.self_attn.o_proj", |
| "model.layers.31.self_attn.qkv_proj", |
| "model.layers.30.mlp.down_proj", |
| "model.layers.30.mlp.gate_up_proj", |
| "model.layers.30.self_attn.o_proj", |
| "model.layers.30.self_attn.qkv_proj", |
| "model.layers.29.mlp.down_proj", |
| "model.layers.29.mlp.gate_up_proj", |
| "model.layers.29.self_attn.o_proj", |
| "model.layers.29.self_attn.qkv_proj", |
| "model.layers.28.mlp.down_proj", |
| "model.layers.28.mlp.gate_up_proj", |
| "model.layers.28.self_attn.o_proj", |
| "model.layers.28.self_attn.qkv_proj", |
| "model.layers.27.mlp.down_proj", |
| "model.layers.27.mlp.gate_up_proj", |
| "model.layers.27.self_attn.o_proj", |
| "model.layers.27.self_attn.qkv_proj", |
| "model.layers.26.mlp.down_proj", |
| "model.layers.26.mlp.gate_up_proj", |
| "model.layers.26.self_attn.o_proj", |
| "model.layers.26.self_attn.qkv_proj", |
| "model.layers.25.mlp.down_proj", |
| "model.layers.25.mlp.gate_up_proj", |
| "model.layers.25.self_attn.o_proj", |
| "model.layers.25.self_attn.qkv_proj", |
| "model.layers.24.mlp.down_proj", |
| "model.layers.24.mlp.gate_up_proj", |
| "model.layers.24.self_attn.o_proj", |
| "model.layers.24.self_attn.qkv_proj", |
| "model.layers.23.mlp.down_proj", |
| "model.layers.23.mlp.gate_up_proj", |
| "model.layers.23.self_attn.o_proj", |
| "model.layers.23.self_attn.qkv_proj", |
| "model.layers.22.mlp.down_proj", |
| "model.layers.22.mlp.gate_up_proj", |
| "model.layers.22.self_attn.o_proj", |
| "model.layers.22.self_attn.qkv_proj", |
| "model.layers.21.mlp.down_proj", |
| "model.layers.21.mlp.gate_up_proj", |
| "model.layers.21.self_attn.o_proj", |
| "model.layers.21.self_attn.qkv_proj", |
| "model.layers.20.mlp.down_proj", |
| "model.layers.20.mlp.gate_up_proj", |
| "model.layers.20.self_attn.o_proj", |
| "model.layers.20.self_attn.qkv_proj", |
| "model.layers.19.mlp.down_proj", |
| "model.layers.19.mlp.gate_up_proj", |
| "model.layers.19.self_attn.o_proj", |
| "model.layers.19.self_attn.qkv_proj", |
| "model.layers.18.mlp.down_proj", |
| "model.layers.18.mlp.gate_up_proj", |
| "model.layers.18.self_attn.o_proj", |
| "model.layers.18.self_attn.qkv_proj", |
| "model.layers.17.mlp.down_proj", |
| "model.layers.17.mlp.gate_up_proj", |
| "model.layers.17.self_attn.o_proj", |
| "model.layers.17.self_attn.qkv_proj", |
| "model.layers.16.mlp.down_proj", |
| "model.layers.16.mlp.gate_up_proj", |
| "model.layers.16.self_attn.o_proj", |
| "model.layers.16.self_attn.qkv_proj", |
| "model.layers.15.mlp.down_proj", |
| "model.layers.15.mlp.gate_up_proj", |
| "model.layers.15.self_attn.o_proj", |
| "model.layers.15.self_attn.qkv_proj", |
| "model.layers.14.mlp.down_proj", |
| "model.layers.14.mlp.gate_up_proj", |
| "model.layers.14.self_attn.o_proj", |
| "model.layers.14.self_attn.qkv_proj", |
| "model.layers.13.mlp.down_proj", |
| "model.layers.13.mlp.gate_up_proj", |
| "model.layers.13.self_attn.o_proj", |
| "model.layers.13.self_attn.qkv_proj", |
| "model.layers.12.mlp.down_proj", |
| "model.layers.12.mlp.gate_up_proj", |
| "model.layers.12.self_attn.o_proj", |
| "model.layers.12.self_attn.qkv_proj", |
| "model.layers.11.mlp.down_proj", |
| "model.layers.11.mlp.gate_up_proj", |
| "model.layers.11.self_attn.o_proj", |
| "model.layers.11.self_attn.qkv_proj", |
| "model.layers.10.mlp.down_proj", |
| "model.layers.10.mlp.gate_up_proj", |
| "model.layers.10.self_attn.o_proj", |
| "model.layers.10.self_attn.qkv_proj", |
| "model.layers.9.mlp.down_proj", |
| "model.layers.9.mlp.gate_up_proj", |
| "model.layers.9.self_attn.o_proj", |
| "model.layers.9.self_attn.qkv_proj", |
| "model.layers.8.mlp.down_proj", |
| "model.layers.8.mlp.gate_up_proj", |
| "model.layers.8.self_attn.o_proj", |
| "model.layers.8.self_attn.qkv_proj", |
| "model.layers.7.mlp.down_proj", |
| "model.layers.7.mlp.gate_up_proj", |
| "model.layers.7.self_attn.o_proj", |
| "model.layers.7.self_attn.qkv_proj", |
| "model.layers.6.mlp.down_proj", |
| "model.layers.6.mlp.gate_up_proj", |
| "model.layers.6.self_attn.o_proj", |
| "model.layers.6.self_attn.qkv_proj", |
| "model.layers.5.mlp.down_proj", |
| "model.layers.5.mlp.gate_up_proj", |
| "model.layers.5.self_attn.o_proj", |
| "model.layers.5.self_attn.qkv_proj", |
| "model.layers.4.mlp.down_proj", |
| "model.layers.4.mlp.gate_up_proj", |
| "model.layers.4.self_attn.o_proj", |
| "model.layers.4.self_attn.qkv_proj", |
| "model.layers.3.mlp.down_proj", |
| "model.layers.3.mlp.gate_up_proj", |
| "model.layers.3.self_attn.o_proj", |
| "model.layers.3.self_attn.qkv_proj", |
| "model.layers.2.mlp.down_proj", |
| "model.layers.2.mlp.gate_up_proj", |
| "model.layers.2.self_attn.o_proj", |
| "model.layers.2.self_attn.qkv_proj", |
| "model.layers.1.mlp.down_proj", |
| "model.layers.1.mlp.gate_up_proj", |
| "model.layers.1.self_attn.o_proj", |
| "model.layers.1.self_attn.qkv_proj", |
| "model.layers.0.mlp.down_proj", |
| "model.layers.0.mlp.gate_up_proj", |
| "model.layers.0.self_attn.o_proj", |
| "model.layers.0.self_attn.qkv_proj" |
| ] |
| }, |
| "rank": 16, |
| "scale": 1.0, |
| "dropout": 0.0, |
| "num_layers": 32, |
| "fine_tune_type": "lora", |
| "peft_type": "LORA", |
| "unsloth_mlx_lora_module_paths": [ |
| "model.layers.31.mlp.down_proj", |
| "model.layers.31.mlp.gate_up_proj", |
| "model.layers.31.self_attn.o_proj", |
| "model.layers.31.self_attn.qkv_proj", |
| "model.layers.30.mlp.down_proj", |
| "model.layers.30.mlp.gate_up_proj", |
| "model.layers.30.self_attn.o_proj", |
| "model.layers.30.self_attn.qkv_proj", |
| "model.layers.29.mlp.down_proj", |
| "model.layers.29.mlp.gate_up_proj", |
| "model.layers.29.self_attn.o_proj", |
| "model.layers.29.self_attn.qkv_proj", |
| "model.layers.28.mlp.down_proj", |
| "model.layers.28.mlp.gate_up_proj", |
| "model.layers.28.self_attn.o_proj", |
| "model.layers.28.self_attn.qkv_proj", |
| "model.layers.27.mlp.down_proj", |
| "model.layers.27.mlp.gate_up_proj", |
| "model.layers.27.self_attn.o_proj", |
| "model.layers.27.self_attn.qkv_proj", |
| "model.layers.26.mlp.down_proj", |
| "model.layers.26.mlp.gate_up_proj", |
| "model.layers.26.self_attn.o_proj", |
| "model.layers.26.self_attn.qkv_proj", |
| "model.layers.25.mlp.down_proj", |
| "model.layers.25.mlp.gate_up_proj", |
| "model.layers.25.self_attn.o_proj", |
| "model.layers.25.self_attn.qkv_proj", |
| "model.layers.24.mlp.down_proj", |
| "model.layers.24.mlp.gate_up_proj", |
| "model.layers.24.self_attn.o_proj", |
| "model.layers.24.self_attn.qkv_proj", |
| "model.layers.23.mlp.down_proj", |
| "model.layers.23.mlp.gate_up_proj", |
| "model.layers.23.self_attn.o_proj", |
| "model.layers.23.self_attn.qkv_proj", |
| "model.layers.22.mlp.down_proj", |
| "model.layers.22.mlp.gate_up_proj", |
| "model.layers.22.self_attn.o_proj", |
| "model.layers.22.self_attn.qkv_proj", |
| "model.layers.21.mlp.down_proj", |
| "model.layers.21.mlp.gate_up_proj", |
| "model.layers.21.self_attn.o_proj", |
| "model.layers.21.self_attn.qkv_proj", |
| "model.layers.20.mlp.down_proj", |
| "model.layers.20.mlp.gate_up_proj", |
| "model.layers.20.self_attn.o_proj", |
| "model.layers.20.self_attn.qkv_proj", |
| "model.layers.19.mlp.down_proj", |
| "model.layers.19.mlp.gate_up_proj", |
| "model.layers.19.self_attn.o_proj", |
| "model.layers.19.self_attn.qkv_proj", |
| "model.layers.18.mlp.down_proj", |
| "model.layers.18.mlp.gate_up_proj", |
| "model.layers.18.self_attn.o_proj", |
| "model.layers.18.self_attn.qkv_proj", |
| "model.layers.17.mlp.down_proj", |
| "model.layers.17.mlp.gate_up_proj", |
| "model.layers.17.self_attn.o_proj", |
| "model.layers.17.self_attn.qkv_proj", |
| "model.layers.16.mlp.down_proj", |
| "model.layers.16.mlp.gate_up_proj", |
| "model.layers.16.self_attn.o_proj", |
| "model.layers.16.self_attn.qkv_proj", |
| "model.layers.15.mlp.down_proj", |
| "model.layers.15.mlp.gate_up_proj", |
| "model.layers.15.self_attn.o_proj", |
| "model.layers.15.self_attn.qkv_proj", |
| "model.layers.14.mlp.down_proj", |
| "model.layers.14.mlp.gate_up_proj", |
| "model.layers.14.self_attn.o_proj", |
| "model.layers.14.self_attn.qkv_proj", |
| "model.layers.13.mlp.down_proj", |
| "model.layers.13.mlp.gate_up_proj", |
| "model.layers.13.self_attn.o_proj", |
| "model.layers.13.self_attn.qkv_proj", |
| "model.layers.12.mlp.down_proj", |
| "model.layers.12.mlp.gate_up_proj", |
| "model.layers.12.self_attn.o_proj", |
| "model.layers.12.self_attn.qkv_proj", |
| "model.layers.11.mlp.down_proj", |
| "model.layers.11.mlp.gate_up_proj", |
| "model.layers.11.self_attn.o_proj", |
| "model.layers.11.self_attn.qkv_proj", |
| "model.layers.10.mlp.down_proj", |
| "model.layers.10.mlp.gate_up_proj", |
| "model.layers.10.self_attn.o_proj", |
| "model.layers.10.self_attn.qkv_proj", |
| "model.layers.9.mlp.down_proj", |
| "model.layers.9.mlp.gate_up_proj", |
| "model.layers.9.self_attn.o_proj", |
| "model.layers.9.self_attn.qkv_proj", |
| "model.layers.8.mlp.down_proj", |
| "model.layers.8.mlp.gate_up_proj", |
| "model.layers.8.self_attn.o_proj", |
| "model.layers.8.self_attn.qkv_proj", |
| "model.layers.7.mlp.down_proj", |
| "model.layers.7.mlp.gate_up_proj", |
| "model.layers.7.self_attn.o_proj", |
| "model.layers.7.self_attn.qkv_proj", |
| "model.layers.6.mlp.down_proj", |
| "model.layers.6.mlp.gate_up_proj", |
| "model.layers.6.self_attn.o_proj", |
| "model.layers.6.self_attn.qkv_proj", |
| "model.layers.5.mlp.down_proj", |
| "model.layers.5.mlp.gate_up_proj", |
| "model.layers.5.self_attn.o_proj", |
| "model.layers.5.self_attn.qkv_proj", |
| "model.layers.4.mlp.down_proj", |
| "model.layers.4.mlp.gate_up_proj", |
| "model.layers.4.self_attn.o_proj", |
| "model.layers.4.self_attn.qkv_proj", |
| "model.layers.3.mlp.down_proj", |
| "model.layers.3.mlp.gate_up_proj", |
| "model.layers.3.self_attn.o_proj", |
| "model.layers.3.self_attn.qkv_proj", |
| "model.layers.2.mlp.down_proj", |
| "model.layers.2.mlp.gate_up_proj", |
| "model.layers.2.self_attn.o_proj", |
| "model.layers.2.self_attn.qkv_proj", |
| "model.layers.1.mlp.down_proj", |
| "model.layers.1.mlp.gate_up_proj", |
| "model.layers.1.self_attn.o_proj", |
| "model.layers.1.self_attn.qkv_proj", |
| "model.layers.0.mlp.down_proj", |
| "model.layers.0.mlp.gate_up_proj", |
| "model.layers.0.self_attn.o_proj", |
| "model.layers.0.self_attn.qkv_proj" |
| ] |
| } |
