| { | |
| "alpha_pattern": {}, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "jonathanjordan21/mos-mamba-18x130m-trainer-dgx-pile", | |
| "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": 64, | |
| "lora_dropout": 0.0, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 64, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "w9", | |
| "w14", | |
| "w6", | |
| "w15", | |
| "w0", | |
| "w8", | |
| "in_proj", | |
| "w16", | |
| "dt_proj", | |
| "w7", | |
| "w1", | |
| "w2", | |
| "w12", | |
| "w11", | |
| "w13", | |
| "w10", | |
| "w5", | |
| "out_proj", | |
| "w3", | |
| "w4", | |
| "gate", | |
| "w17" | |
| ], | |
| "task_type": "CAUSAL_LM", | |
| "use_dora": false, | |
| "use_rslora": false | |
| } |