SkyColThreeCat

/

MedMLIP_GuidedByQwen3B

Like 0

This PR adds a model card for the MedMLIP visual encoder described in the paper Pretraining of Medical Visual Encoders Toward Multi-modal Large Language Models. It adds the pipeline_tag (image-feature-extraction), library_name (transformers), links to the paper and GitHub repository, and a usage example for extracting patch features with CLIPVisionModel.