Improve model card for Switch Generation model with paper, GitHub links, usage, and metadata

#1
by nielsr HF Staff - opened

This PR significantly improves the model card for the "Switch Generation" model.

Key updates include:

  • Comprehensive Description: The boilerplate text has been replaced with a detailed summary derived from the paper's abstract, explaining the novel "Switch Generation" concept.
  • Metadata Enrichment:
    • The pipeline_tag: text-generation has been added for better discoverability on the Hugging Face Hub.
    • Relevant tags such as llama, model-collaboration, and instruction-following have been included.
    • The base_model has been explicitly listed (allenai/Llama-3.1-Tulu-3-8B).
    • The license is set to other as no explicit license was found in the source materials.
  • Linked Resources: Direct links to the academic paper (Don't Throw Away Your Pretrained Model) and the associated GitHub repository (https://github.com/BunsenFeng/switch_generation) have been added.
  • Getting Started Guide: A "How to Get Started" section, including code snippets for environment setup and inference, has been extracted directly from the GitHub README.

These changes make the model card much more informative and user-friendly for researchers and practitioners.

bunsenfeng changed pull request status to merged

Sign up or log in to comment