How to use endishai/qwen2.5-32b-lexenvs-grpo-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct") model = PeftModel.from_pretrained(base_model, "endishai/qwen2.5-32b-lexenvs-grpo-lora")
How to fix it?
