How to use Myashka/LLama_RLHF_SO with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("decapoda-research/llama-7b-hf") model = PeftModel.from_pretrained(base_model, "Myashka/LLama_RLHF_SO")
RLHF training upon Myashka/LLama_SO_SFT SFT LoRA adapter