Add pipeline tag and enrich model card content
#1
by
nielsr
HF Staff
- opened
This PR improves the model card for shufanshen/VL-SAE by:
- Adding the
pipeline_tag: zero-shot-image-classification: This tag enhances the model's discoverability on the Hugging Face Hub, as the model contributes to performance improvements in this downstream task. - Enriching the model card with the paper's abstract: The full abstract of the paper "VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set" is included to provide comprehensive context about the model's purpose, methodology, and capabilities.
- Including the BibTeX citation: The official BibTeX citation from the GitHub repository is added for proper academic attribution.
These changes provide more complete and accessible information for users and researchers.
Hi there! Thanks so much for putting together this PR with these valuable improvements.
I actually just updated the model card myself with similar changes based on your suggestions, which is why there might be a merge conflict. And I really appreciate you taking the time to flag these details.
I’ll go ahead and close this PR since the updates are now live.
Thanks again for your help making the model more accessible!
shufanshen
changed pull request status to
closed