How to use amit51/cybersoc-arena-qwen2.5-1.5b-grpo with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct") model = PeftModel.from_pretrained(base_model, "amit51/cybersoc-arena-qwen2.5-1.5b-grpo")
https://huggingface.co/amit51/cybersoc-arena-qwen2.5-1.5b-grpo/resolve/main/grpo_baseline_compare.png
hf download hf://amit51/cybersoc-arena-qwen2.5-1.5b-grpo/grpo_baseline_compare.png
curl -L -o grpo_baseline_compare.png https://huggingface.co/amit51/cybersoc-arena-qwen2.5-1.5b-grpo/resolve/main/grpo_baseline_compare.png
