How to use vivekraina/falcon-7b-4bit with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("vilsonrodrigues/falcon-7b-instruct-sharded") model = PeftModel.from_pretrained(base_model, "vivekraina/falcon-7b-4bit")