| { | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "ycchen/yc-test1", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "lora_alpha": 16, | |
| "lora_dropout": 0.05, | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 32, | |
| "revision": null, | |
| "target_modules": [ | |
| "28.attn.c_attn", | |
| "28.attn.c_proj", | |
| "28.mlp.c_proj", | |
| "28.mlp.w1", | |
| "28.mlp.w2", | |
| "29.attn.c_attn", | |
| "29.attn.c_proj", | |
| "29.mlp.c_proj", | |
| "29.mlp.w1", | |
| "29.mlp.w2", | |
| "30.attn.c_attn", | |
| "30.attn.c_proj", | |
| "30.mlp.c_proj", | |
| "30.mlp.w1", | |
| "30.mlp.w2", | |
| "31.attn.c_attn", | |
| "31.attn.c_proj", | |
| "31.mlp.c_proj", | |
| "31.mlp.w1", | |
| "31.mlp.w2", | |
| "32.attn.c_attn", | |
| "32.attn.c_proj", | |
| "32.mlp.c_proj", | |
| "32.mlp.w1", | |
| "32.mlp.w2", | |
| "33.attn.c_attn", | |
| "33.attn.c_proj", | |
| "33.mlp.c_proj", | |
| "33.mlp.w1", | |
| "33.mlp.w2", | |
| "34.attn.c_attn", | |
| "34.attn.c_proj", | |
| "34.mlp.c_proj", | |
| "34.mlp.w1", | |
| "34.mlp.w2", | |
| "35.attn.c_attn", | |
| "35.attn.c_proj", | |
| "35.mlp.c_proj", | |
| "35.mlp.w1", | |
| "35.mlp.w2", | |
| "36.attn.c_attn", | |
| "36.attn.c_proj", | |
| "36.mlp.c_proj", | |
| "36.mlp.w1", | |
| "36.mlp.w2", | |
| "37.attn.c_attn", | |
| "37.attn.c_proj", | |
| "37.mlp.c_proj", | |
| "37.mlp.w1", | |
| "37.mlp.w2", | |
| "38.attn.c_attn", | |
| "38.attn.c_proj", | |
| "38.mlp.c_proj", | |
| "38.mlp.w1", | |
| "38.mlp.w2", | |
| "39.attn.c_attn", | |
| "39.attn.c_proj", | |
| "39.mlp.c_proj", | |
| "39.mlp.w1", | |
| "39.mlp.w2" | |
| ], | |
| "task_type": "CAUSAL_LM" | |
| } |