nhanv
/

dolly_open_llama_3b_reward_lora

Model card Files Files and versions Community

dolly_open_llama_3b_reward_lora / finetuning_args.json

nhanv

upload

5b84239 12 months ago

raw history blame contribute delete

No virus

235 Bytes

	{
	"finetuning_type": "lora",
	"lora_alpha": 32.0,
	"lora_dropout": 0.1,
	"lora_rank": 8,
	"lora_target": [
	"q_proj",
	"v_proj"
	],
	"name_module_trainable": "mlp",
	"num_hidden_layers": 32,
	"num_layer_trainable": 3
	}