|
{ |
|
"alpha_pattern": {}, |
|
"auto_mapping": null, |
|
"base_model_name_or_path": "bigscience/mt0-large", |
|
"beta1": 0.85, |
|
"beta2": 0.85, |
|
"bias": "none", |
|
"deltaT": 1, |
|
"fan_in_fan_out": false, |
|
"inference_mode": true, |
|
"init_lora_weights": true, |
|
"init_r": 12, |
|
"layers_pattern": null, |
|
"layers_to_transform": null, |
|
"loftq_config": {}, |
|
"lora_alpha": 32, |
|
"lora_dropout": 0.1, |
|
"megatron_config": null, |
|
"megatron_core": "megatron.core", |
|
"modules_to_save": null, |
|
"orth_reg_weight": 0.5, |
|
"peft_type": "ADALORA", |
|
"r": 8, |
|
"rank_pattern": null, |
|
"revision": null, |
|
"target_modules": [ |
|
"q", |
|
"k", |
|
"v", |
|
"o", |
|
"wi_0", |
|
"wi_1", |
|
"wo" |
|
], |
|
"target_r": 8, |
|
"task_type": "SEQ_2_SEQ_LM", |
|
"tfinal": 0, |
|
"tinit": 0, |
|
"total_step": null |
|
} |