Improve model card: Add `library_name`, expanded description, GitHub link, and usage

#1
by nielsr HF Staff - opened

This PR significantly improves the model card for sunblaze-ucb/Qwen2.5-3B-Intuitor-MATH-1EPOCH.

Key improvements include:

  • Adding the library_name: transformers metadata tag to enable the "How to use" widget on the Hugging Face Hub.
  • Expanding the model description with an introduction to Intuitor and RLIF, based on the accompanying paper Learning to Reason without External Rewards.
  • Adding a direct link to the project's GitHub repository for easy access to the code and further details.
  • Including a clear Python code snippet demonstrating how to use the model for text generation with the transformers library, specifically utilizing its chat template.

Please review and merge this PR to enhance the model's discoverability and usability on the Hub.

Xuandong changed pull request status to merged

Sign up or log in to comment