How to use feedback-to-code/swe-diff-llama-3-8B-Instruct-First with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-Instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "feedback-to-code/swe-diff-llama-3-8B-Instruct-First")
philippkolbe commited on 
