Improve model card: Add pipeline tag, paper/code links, and detailed information

#8
by nielsr HF Staff - opened

This PR significantly enhances the model card for the SimVQ model by:

  • Adding the pipeline_tag: image-to-image to the metadata, which helps users discover the model for relevant tasks on the Hub.
  • Including a comprehensive description of the model based on the paper's abstract.
  • Providing a direct link to the official paper on Hugging Face (https://huggingface.co/papers/2411.02038).
  • Adding a link to the official GitHub repository (https://github.com/youngsheen/SimVQ) for easy access to the code.
  • Incorporating quantitative comparison tables from the GitHub README, showcasing the model's performance on both image and audio tasks.
  • Adding reconstruction visualizations for both image and audio, linking to the raw assets on GitHub.
  • Including a BibTeX citation for the paper.

These changes make the model card more informative, discoverable, and aligned with best practices for documenting artifacts on the Hugging Face Hub.

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment