This PR enhances the model card by adding:
- The `library_name` tag, enabling the "how to use" widget for `transformers`.
- The `pipeline_tag: image-text-to-text`, improving discoverability on the Hugging Face Hub.
- A link to the associated paper: [Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens](https://huggingface.co/papers/2511.19418).
- A link to the project page: https://wakalsprojectpage.github.io/comt-website.
- A link to the GitHub repository: https://github.com/Wakals/CoMT.
- An expanded model description that includes an overview of the CoVT framework for better context.
Please review and merge if everything looks good!
