Add model card with pipeline tag, paper, code, and usage example
#1
by
nielsr
HF Staff
- opened
This pull request significantly enhances the model card for SmartCLIP by:
- Adding the
pipeline_tag: zero-shot-image-classificationto the metadata, making the model discoverable on the Hugging Face Hub by its primary task. - Including a direct link to the paper: SmartCLIP: Modular Vision-language Alignment with Identification Guarantees.
- Adding a link to the official GitHub repository for the code:
https://github.com/MidPush/SmartCLIP. - Including the paper's abstract for quick context.
- Providing a runnable Python code snippet for quick inference, along with instructions for setup and checkpoint download.
- Adding a BibTeX citation for proper academic attribution.
These additions greatly improve the usability and discoverability of the model. Please review and merge.