Wakals

/

CoVT-7B-seg

like 1

This PR enhances the model card for the CoVT checkpoint by:

• Adding the pipeline_tag: image-text-to-text for better discoverability on the Hub.
• Adding library_name: transformers to indicate compatibility and enable the "how to use" widget.
• Including direct links to the paper (Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens), the project page (https://wakalsprojectpage.github.io/comt-website), and the GitHub repository (https://github.com/Wakals/CoMT).
• Expanding the model description with an overview of the CoVT framework, extracted from the paper's main concepts.
• Embedding key demonstration images from the GitHub repository.
• Adding a BibTeX citation for the paper.

These updates will make the model card more informative, accessible, and user-friendly.