Improve model card with abstract, sample usage, and detailed information
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card by:
- Fixing a minor HTML typo in the main heading (
</h1h1>to</h1>). - Adding the paper abstract for better context and understanding.
- Updating the "Highlights" section with more descriptive points from the GitHub README.
- Expanding the "Model Weights" table to include both 2B and 9B model checkpoints, providing a complete overview of released models.
- Incorporating a "Sample Usage" section with Python code snippets directly from the GitHub repository, demonstrating how to use the model with the
transformerslibrary for image captioning and multi-turn chat. - Adding a comprehensive "Benchmark Results" table to showcase the model's performance across various vision-language tasks.
- Including the "Todo List" from the GitHub README for transparency on development plans.
These updates make the model card more informative, user-friendly, and aligned with best practices for documentation on the Hugging Face Hub.