How to use palmfuture/gemma-4-12B-it-FP8 with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("palmfuture/gemma-4-12B-it-FP8") model = AutoModelForImageTextToText.from_pretrained("palmfuture/gemma-4-12B-it-FP8")
palmfuture commited on 