| { | |
| "adapter_labels": [ | |
| "ALL" | |
| ], | |
| "alpha_pattern": {}, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "ai-forever/mGPT", | |
| "bias": "none", | |
| "exclude_modules": null, | |
| "fan_in_fan_out": true, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layer_group": 0, | |
| "layer_replication": null, | |
| "layers_pattern": "h", | |
| "layers_to_transform": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 19, | |
| 20, | |
| 21 | |
| ], | |
| "loftq_config": {}, | |
| "lora_alpha": 128, | |
| "lora_dropout": 0.1, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": null, | |
| "num_adapters_per_layer": 1, | |
| "peft_type": "LORA", | |
| "r": 64, | |
| "r_a": [ | |
| 64 | |
| ], | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "c_proj", | |
| "c_attn" | |
| ], | |
| "task_type": "CAUSAL_LM", | |
| "use_dora": false, | |
| "use_rslora": false | |
| } |