trinhvg

/

ViDRiP_LLaVA_image

like 0

This PR enhances the model card for ViDRiP-LLaVA by:

• Adding pipeline_tag: video-text-to-text to improve discoverability on the Hub.
• Specifying library_name: transformers based on config.json evidence (LlavaQwenForCausalLM architecture) to enable the "How to use" widget and provide a standard inference snippet.
• Including additional descriptive tags such as medical, pathology, video-language-model, VLM, and LLaVA.
• Adding a prominent link to the Hugging Face paper page: https://huggingface.co/papers/2505.04192.
• Adding a prominent link to the GitHub repository: https://github.com/trinhvg/VideoPath-LLaVA.

These changes aim to make the model card more informative and discoverable.