rzzhan

/

ExGRPO-Qwen2.5-7B-Instruct

like 0

This PR adds a comprehensive model card for the ExGRPO model.
It includes:

• Relevant metadata (license: apache-2.0, library_name: transformers, pipeline_tag: text-generation).
• A link to the paper: ExGRPO: Learning to Reason from Experience.
• A link to the official GitHub repository: https://github.com/ElliottYan/LUFFY/tree/main/ExGRPO.
• An overview of the model, including key highlights and an illustrative image from the GitHub README.
• A link to the Hugging Face Collection associated with ExGRPO.
• The BibTeX citation for the paper.

These additions will significantly improve the discoverability and usability of this model on the Hugging Face Hub. Please review and merge.