30 lines
671 B
JSON
30 lines
671 B
JSON
{
|
|
"alpha_pattern": {},
|
|
"auto_mapping": null,
|
|
"base_model_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
|
|
"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": 0.05,
|
|
"megatron_config": null,
|
|
"megatron_core": "megatron.core",
|
|
"modules_to_save": null,
|
|
"peft_type": "LORA",
|
|
"r": 32,
|
|
"rank_pattern": {},
|
|
"revision": null,
|
|
"target_modules": [
|
|
"down_proj",
|
|
"gate_proj",
|
|
"up_proj"
|
|
],
|
|
"task_type": "CAUSAL_LM",
|
|
"use_dora": false,
|
|
"use_rslora": false
|
|
} |