groffo

/

infinite-self-attention

like 0

Hi! I'm Niels from the community team at Hugging Face.

This PR improves the model card by adding essential metadata:

• pipeline_tag: Set to image-classification as the paper focuses heavily on Vision Transformers and ImageNet benchmarks.
• library_name: Set to transformers as the README provides clear evidence and code snippets for using InfSA with Hugging Face models.
• license: Set to mit as indicated in the original repository.
• Paper Link: Added a link to the research paper on the Hugging Face Hub to help users discover and cite your work.

These changes will improve the discoverability of your work on the Hub. Let me know if you have any questions!