PEFT How to use xiaojuntime/final-ppo with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("xiaojuntime/peft-merged")
model = PeftModel.from_pretrained(base_model, "xiaojuntime/final-ppo") 
