TMLR-Group-HF

/

Entropy-Qwen2.5-7B-MATH

like 1

Follow

TMLR Group 20

This PR enhances the model card for the TMLR-Group-HF/Entropy-Qwen2.5-7B model by:

• Adding pipeline_tag: text-generation to improve discoverability on the Hugging Face Hub.
• Specifying library_name: transformers based on config.json and tokenizer_config.json to enable automated "how-to-use" code snippets.
• Integrating a direct link to the official paper: Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models.
• Correcting the GitHub repository link to https://github.com/tmlr-group/Co-rewarding for accuracy.
• Expanding the model description with a concise summary from the paper's abstract to provide more context about the Co-rewarding framework.
• Updating the citation section to use a proper BibTeX block and ensure the paper title matches the official publication.

These changes aim to make the model card more informative, discoverable, and user-friendly.