Documentation on MMBTModel, MMBTConfig and using the MMBT model in general

I’m new to using HuggingFace, but I really like their API so far. I’m looking to use a multimodal model to use on a text-image dataset and saw they had one called MMBT. Is there a page with more documentation on how to use the functions MMBTModel and MMBTConfig since the only page of documentation on MMBT I could find was this.