PEFT How to use mlrun/gemma-2b-bank with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("google/gemma-2b")
model = PeftModel.from_pretrained(base_model, "mlrun/gemma-2b-bank") 
