Improve model card: Update pipeline tag, add comprehensive details and demos

by nielsr HF Staff - opened Jul 1

←

nielsr

Jul 1

This PR significantly enhances the model card for WebDancer by:

Updating the pipeline_tag from text-generation to image-text-to-text to accurately reflect the model's multimodal capabilities in processing visual inputs (e.g., GUI screenshots) for web interaction. This ensures the model is discoverable under the correct pipeline at https://huggingface.co/models?pipeline_tag=image-text-to-text.
Adding relevant tags such as web-agent, gui-agent, multimodal, reinforcement-learning, and react for improved discoverability and context.
Including the paper abstract for a concise overview.
Explicitly linking to the GitHub repository for code and project details.
Incorporating detailed "Features", "Quick Start" instructions, and embedded "Demos" from the project's GitHub README to provide a comprehensive understanding and easier usability.
Adding the academic citation for proper attribution.

This update makes the model card more informative, accessible, and aligned with Hugging Face Hub best practices.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment