Wakals

/

CoVT-LLaVA-13B-depth

like 2

This PR enhances the model card by adding key metadata and comprehensive information:

• Adds pipeline_tag: image-text-to-text to correctly categorize the model for multimodal tasks.
• Adds library_name: transformers as the model architecture (llava_llama and AnchorLlava) and transformers_version in config.json indicate compatibility with the transformers library, enabling the "How to use" widget.
• Includes a direct link to the paper: Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens.
• Provides links to the official project page (https://wakalsprojectpage.github.io/comt-website) and the GitHub repository (https://github.com/Wakals/CoMT) for easy access to more resources.
• Expands the "Model Description" with a detailed overview of CoVT's methodology and benefits, derived from the paper's abstract and the GitHub README.
• Embeds relevant demo images from the GitHub repository to visually illustrate the model's capabilities.
• Adds a BibTeX citation for the paper.

Please review and merge if these improvements align with your expectations.