PEFT How to use Heng666/phi-2-qlora with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2")
model = PeftModel.from_pretrained(base_model, "Heng666/phi-2-qlora") 
