How to use thejaminator/grpo-5e-6_kl_64_clip_higher_binary-step-30 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B") model = PeftModel.from_pretrained(base_model, "thejaminator/grpo-5e-6_kl_64_clip_higher_binary-step-30")
Base model
