MedVLSynther

/

MedVLSynther-7B-RL_10K

like 0

Follow

MedVLSynther 3

This PR enhances the model card for MedVLSynther-7B-RL_10K by adding essential metadata and improving content structure:

• pipeline_tag: image-text-to-text: This tag is added to the metadata to accurately categorize the model as a multimodal Vision-Language Model capable of generating text from image and text inputs, improving its discoverability on the Hugging Face Hub.
• library_name: transformers: Evidence from the provided usage example shows compatibility with the transformers library, so this tag is added to the metadata. This will enable the automatic "How to use" widget on the model page, providing users with a ready-to-run code snippet.
• Explicit Paper Link: An explicit link to the paper, MedVLSynther: Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs, has been added to the model card's content for easier access and improved documentation.

These changes improve the model's discoverability and user experience on the Hugging Face Hub.