Mistral Adapter as starting point for Resolving Interference When Merging Models ("ties") MoE
2426ab5
| { | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "/run/media/knut/HD2/Yarn-Mistral-7b-128k/", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.05, | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 16, | |
| "revision": null, | |
| "target_modules": [ | |
| "q_proj", | |
| "k_proj", | |
| "v_proj", | |
| "o_proj" | |
| ], | |
| "task_type": "CAUSAL_LM" | |
| } |