PEFT How to use dodo2/gemma-3-4bit_finevision with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-4b-it")
model = PeftModel.from_pretrained(base_model, "dodo2/gemma-3-4bit_finevision") 
