Improve model card: Add Tequila paper details, metadata, and update tags

#3
by nielsr HF Staff - opened

This PR improves the model card for the AngelSlim toolkit, focusing on the Tequila quantization method presented in the paper "Tequila: Trapping-free Ternary Quantization for Large Language Models".

Key changes include:

  • Added metadata:
    • pipeline_tag: text-generation for improved discoverability.
    • library_name: transformers based on config.json and usage patterns.
    • license: apache-2.0 derived from the project's GitHub repository.
  • Updated tags: Added quantization to reflect the Tequila method.
  • Enhanced content:

These updates aim to make the model card more informative and discoverable while accurately representing the capabilities of the AngelSlim project.

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment