How to use nisten/13b8bitresults with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-13b-hf") model = PeftModel.from_pretrained(base_model, "nisten/13b8bitresults")
nisten commited on 