42 lines
907 B
JSON
42 lines
907 B
JSON
|
{
|
||
|
|
"alpha_pattern": {},
|
||
|
|
"auto_mapping": null,
|
||
|
|
"base_model_name_or_path": "/mnt/e/AI/Project02/AITrain/Qwen/Qwen3-4B",
|
||
|
|
"bias": "none",
|
||
|
|
"corda_config": null,
|
||
|
|
"eva_config": null,
|
||
|
|
"exclude_modules": null,
|
||
|
|
"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": 16,
|
||
|
|
"lora_bias": false,
|
||
|
|
"lora_dropout": 0.1,
|
||
|
|
"megatron_config": null,
|
||
|
|
"megatron_core": "megatron.core",
|
||
|
|
"modules_to_save": [
|
||
|
|
"lm_head",
|
||
|
|
"embed_tokens"
|
||
|
|
],
|
||
|
|
"peft_type": "LORA",
|
||
|
|
"r": 8,
|
||
|
|
"rank_pattern": {},
|
||
|
|
"revision": null,
|
||
|
|
"target_modules": [
|
||
|
|
"k_proj",
|
||
|
|
"v_proj",
|
||
|
|
"q_proj",
|
||
|
|
"o_proj",
|
||
|
|
"up_proj",
|
||
|
|
"gate_proj",
|
||
|
|
"down_proj"
|
||
|
|
],
|
||
|
|
"task_type": "CAUSAL_LM",
|
||
|
|
"trainable_token_indices": null,
|
||
|
|
"use_dora": false,
|
||
|
|
"use_rslora": false
|
||
|
|
}
|