How to use this BioViL-T Model
#1
by
murat-gunay
- opened
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.
ozanoktay
changed discussion status to
closed