How to use lukaspetersson/Qwen2-0.5B-LoRA-Reward-Math-Shepherd with PEFT:
from peft import PeftModel from transformers import AutoModelForTokenClassification base_model = AutoModelForTokenClassification.from_pretrained("Qwen/Qwen2-0.5B") model = PeftModel.from_pretrained(base_model, "lukaspetersson/Qwen2-0.5B-LoRA-Reward-Math-Shepherd")
