GSAI-ML

/

ESPO-MATH

like 0

Follow

GSAI-ML 257

This PR significantly enhances the model card for the ESPO (ELBO-based Sequence-level Policy Optimization) model by:

• Adding pipeline_tag: text-generation for better discoverability on the Hub.
• Adding library_name: transformers to correctly identify its compatibility and enable the "how to use" widget.
• Including a concise introduction to the ESPO framework based on the paper's abstract and GitHub README.
• Linking to the official Hugging Face paper page: Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective.
• Adding a link to the project page: https://jingyangou.github.io/ESPO-Demo/.
• Providing a link to the GitHub repository: https://github.com/ML-GSAI/ESPO.
• Incorporating a "Quick Start" section with a Python code snippet for immediate sample usage, directly sourced from the GitHub README.
• Adding the BibTeX citation for proper academic attribution.

Please review and merge this PR if everything looks good.