|
{ |
|
"alpha_pattern": {}, |
|
"auto_mapping": null, |
|
"base_model_name_or_path": "google/flan-t5-large", |
|
"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": 32, |
|
"lora_dropout": 0.05, |
|
"megatron_config": null, |
|
"megatron_core": "megatron.core", |
|
"modules_to_save": null, |
|
"peft_type": "LORA", |
|
"r": 16, |
|
"rank_pattern": {}, |
|
"revision": null, |
|
"target_modules": [ |
|
"decoder.block.15.layer.0.SelfAttention.q", |
|
"encoder.block.7.layer.0.SelfAttention.v", |
|
"encoder.block.4.layer.0.SelfAttention.q", |
|
"decoder.block.1.layer.1.EncDecAttention.q", |
|
"decoder.block.16.layer.0.SelfAttention.v", |
|
"decoder.block.15.layer.1.EncDecAttention.v", |
|
"encoder.block.20.layer.0.SelfAttention.q", |
|
"encoder.block.20.layer.0.SelfAttention.v", |
|
"encoder.block.16.layer.0.SelfAttention.q", |
|
"decoder.block.10.layer.1.EncDecAttention.q", |
|
"decoder.block.22.layer.1.EncDecAttention.v", |
|
"encoder.block.8.layer.0.SelfAttention.q", |
|
"decoder.block.0.layer.0.SelfAttention.v", |
|
"decoder.block.18.layer.1.EncDecAttention.q" |
|
], |
|
"task_type": "SEQ_2_SEQ_LM", |
|
"use_dora": false, |
|
"use_rslora": false |
|
} |