| { | |
| "alpha_pattern": {}, | |
| "auto_mapping": { | |
| "base_model_class": "LLaDAModelLM", | |
| "parent_library": "transformers_modules.GSAI-ML.LLaDA-8B-Base.0f2787f2d87eac5eed8a087d5ecd24277e6255b2.modeling_llada" | |
| }, | |
| "base_model_name_or_path": "GSAI-ML/LLaDA-8B-Base", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 256, | |
| "lora_dropout": 0.05, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 128, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "gate_proj", | |
| "k_proj", | |
| "up_proj", | |
| "q_proj", | |
| "v_proj", | |
| "down_proj", | |
| "o_proj" | |
| ], | |
| "task_type": null, | |
| "use_dora": false, | |
| "use_rslora": false | |
| } |