How to use NehaChikle/kaizen-grpo with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "NehaChikle/kaizen-grpo")
Fine-tuned Qwen2.5-3B-Instruct with GRPO for OS management tasks.
Chat template
Files info
