Add model card for Reinforced Visual Perception with Tools
#1
by
nielsr
HF Staff
- opened
This PR significantly improves the model card for "Reinforced Visual Perception with Tools" by:
- Adding the
pipeline_tag: image-text-to-textto enable better discoverability on the Hugging Face Hub, reflecting the model's multi-modal capabilities. - Adding the
library_name: transformersto indicate compatibility and enable the automated usage widget. - Linking the model to its official paper: Reinforced Visual Perception with Tools.
- Providing a direct link to the GitHub repository for code and further details: https://github.com/ls-kelvin/REVPT.
- Including a link to the associated Hugging Face collection for models and datasets: https://huggingface.co/collections/Frywind/revpt-68b05161d2426128ea5db4d3.
- Incorporating the paper's abstract to give users a comprehensive overview of the research.
Please review and merge this PR.
Thank you for your contribution!
Frywind
changed pull request status to
merged