PEFT How to use smjain/z3-api-reasoning-ppo with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B")
model = PeftModel.from_pretrained(base_model, "smjain/z3-api-reasoning-ppo")