Lexsi

/

Orion-BiX

like 1

Follow

Lexsi Labs 9

This PR significantly enhances the model card by incorporating rich, detailed content from the GitHub repository, making it more informative and useful for the community.

Key improvements include:

• Adding the pipeline_tag: table-question-answering to the metadata, which improves discoverability on the Hugging Face Hub.
• Adding a direct link to the paper: Orion-Bix: Bi-Axial Attention for Tabular In-Context Learning.
• Listing the authors of the paper: Mohamed Bouadi, Pratinav Seth, Aditya Tanna, Vinay Kumar Sankarapu.
• Including a link to the project homepage: https://www.lexsi.ai/.
• Integrating detailed sections on the model's approach, architecture, installation, usage, preprocessing, and performance metrics directly from the GitHub README.
• Preserving the logo.png image path to maintain existing functionality while using figures/ paths for new performance images from the GitHub README.
• Updating the citation section with the more comprehensive BibTeX entry from the GitHub repository.

Please review these updates.