TMLR-Group-HF

/

Self-Certainty-Qwen2.5-7B-MATH

like 1

Follow

TMLR Group 17

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

• Adding pipeline_tag: text-generation: This categorizes the model correctly for better discoverability on the Hugging Face Hub, aligning with its function for reasoning in LLMs.
• Adding library_name: transformers: This indicates compatibility with the transformers library, enabling an automated inference widget and showcasing typical usage.
• Linking to the official Hugging Face paper page: Providing a direct link to Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models for comprehensive paper details.
• Correcting the GitHub repository link: Updating the link to the accurate project repository: https://github.com/tmlr-group/Co-rewarding.
• Updating the Citation: Ensuring the citation block reflects the correct paper title and author list as found in the official GitHub repository and paper.

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