How to use google/gemma-4-12B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/gemma-4-12B") model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-12B")
Hello!
The unified version is said to not have any encoders. Does this means I can input image with any resolution or aspect ratio, and audio with any sample rate or channel amount (e.g., mono, stereo)? And how video is handled?
Thanks!
· Sign up or log in to comment
