Transformers How to use lamm-mit/google-gemma-4-E4B-it with Transformers:
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM
processor = AutoProcessor.from_pretrained("lamm-mit/google-gemma-4-E4B-it")
model = AutoModelForMultimodalLM.from_pretrained("lamm-mit/google-gemma-4-E4B-it", device_map="auto") 
