yhx12

/

VideoSSR

like 2

This PR enhances the model card for VideoSSR-8B by:

• Adding pipeline_tag: video-text-to-text to improve discoverability on the Hugging Face Hub.
• Specifying library_name: transformers as the model's config.json indicates compatibility with the transformers library, enabling the automated "how to use" widget.
• Adding license: apache-2.0, inferred from related project code.
• Including the paper's abstract and authors for a more complete overview of the research.
• Expanding the content with relevant descriptions, badges linking to associated Hugging Face datasets and benchmarks, and images directly from the GitHub repository to provide richer context about the model, its pretext tasks, and performance.

The existing arXiv paper link has been kept as per instructions, and a sample usage section has not been added as no direct inference code was found in the provided GitHub README.