gpt4-alpaca-lora_mlp-65b / adapter_config.json
chtan's picture
10 epochs and rank set to 16
3d067d8
raw
history blame
408 Bytes
{
"base_model_name_or_path": "/cache1/chtan/large_models/llama-hf/llama-65b",
"bias": "none",
"enable_lora": null,
"fan_in_fan_out": false,
"inference_mode": true,
"lora_alpha": 16,
"lora_dropout": 0.05,
"merge_weights": false,
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"target_modules": [
"gate_proj",
"down_proj",
"up_proj"
],
"task_type": "CAUSAL_LM"
}