How to enable audio and vision modalities in tunix's gemma4?

[syrkis]

Unlike gemma3, tunix gemma4, does not take a text_only=False parameter. How do I enable to vision and audio modalities?

[ridcl]

Looking at the code, I believe audio and vision encoders are not implemented here yet.
So the question is, should we expect multimodality added to Gemma 4 in Tunix anytime soon?