How to use helloAK96/chaosops-grpo-lora-p3a with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct") model = PeftModel.from_pretrained(base_model, "helloAK96/chaosops-grpo-lora-p3a")