Add model card and metadata for dUltra

#1
by nielsr HF Staff - opened

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

This PR adds a model card for dUltra, an on-policy reinforcement learning framework for masked diffusion language models.

The PR includes:

  • Relevant metadata (pipeline tag and library name).
  • Links to the paper and the official GitHub repository.
  • A summary of the model's architecture and training approach.
  • A sample usage code snippet based on the official README.
  • BibTeX citation information.

Please feel free to merge if this looks good to you!

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

Sign up or log in to comment