UserJoseph

/

DisTime-8B

like 0

This PR significantly improves the model card for the DisTime model by adding crucial metadata and comprehensive usage instructions.

Specifically, this PR:

• Adds the pipeline_tag: video-text-to-text, ensuring the model is discoverable in relevant searches on the Hugging Face Hub.
• Adds library_name: transformers to indicate compatibility with the Hugging Face transformers library, enabling the "How to use" widget on the model page.
• Links the model to its official Hugging Face Paper page: DisTime: Distribution-based Time Representation for Video Large Language Models.
• Includes a link to the official GitHub repository for easy access to the codebase.
• Provides a detailed "Usage" section with a Python code example demonstrating inference using the transformers library.
• Integrates the paper's abstract, key images (network diagram, InternVid-TG dataset examples), models and data information, citation, and acknowledgements from the original GitHub repository for a complete overview.

This improvement aims to make the model more discoverable and user-friendly for the community.