How to use pablomiralles22/Qwen2.5-7B-GRPO_r32-NLI with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct") model = PeftModel.from_pretrained(base_model, "pablomiralles22/Qwen2.5-7B-GRPO_r32-NLI")
pablomiralles22 commited on 