TMLR-Group-HF

/

Majority-Voting-Qwen3-8B-Base-MATH

like 1

Follow

TMLR Group 17

This PR improves the model card by:

• Adding the pipeline_tag: text-generation to improve discoverability on the Hugging Face Hub.
• Adding library_name: transformers to enable the automated "how to use" widget, as the model is compatible with the transformers library.
• Linking directly to the official Hugging Face paper page: Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models.
• Providing a brief summary of the paper's abstract to give users more context about the Co-rewarding framework.
• Correcting the GitHub repository link from https://github.com/tmlr-group/Co-Reward to https://github.com/tmlr-group/Co-rewarding to match the canonical repository URL.