Improve model card: Add paper, code links, pipeline tag, usage, and trained models

#1
by nielsr HF Staff - opened

This PR significantly enhances the model card by:

  • Adding the pipeline_tag: text-generation to the metadata, which will enable the inference widget and improve discoverability.
  • Linking the model to its official paper: Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning.
  • Providing a direct link to the associated GitHub repository.
  • Including a concise description of the model based on the paper's abstract.
  • Adding a "Sample Usage" section with a Python code snippet, directly sourced from the GitHub README, demonstrating how to load the model.
  • Incorporating the table of other trained model weights from the GitHub README to provide more context about the project's artifacts.
  • Removing the internal "File information" section.

Please review and merge if everything looks good!

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

Sign up or log in to comment