How to use this BioViL-T Model
This model does not belong to any "task" and there is no documentation about this architecture "CXRBertModel" which is not correct I guess. This model is based on vision and text (multimodal) so there is not enough script for getting prediction.
Thanks for your message. Please check "how-to-use" section in the documentation:
https://huggingface.co/microsoft/BiomedVLP-BioViL-T#how-to-use
It demonstrates a way to obtain text embeddings using the released model weights.
Same error happened to me.
The example did'nt works.
ValueError: The model class you are passing has a config_class attribute that is not consistent with the config class you passed (model has <class 'transformers_modules.microsoft.BiomedVLP-BioViL-T.301f526e823b805d3fe712d0cf06a66f042789c5.configuration_cxrbert.CXRBertConfig'> and you passed <class 'transformers.models.bert.configuration_bert.BertConfig'>. Fix one of those so they match!