TMLR-Group-HF

/

Self-Certainty-Qwen3-8B-Base-MATH

like 1

Follow

TMLR Group 20

This PR updates the model card for Self-Certainty-Qwen3-8B-Base, linking it to its corresponding paper: Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models.

It also adds:

• pipeline_tag: text-generation, making the model discoverable under the text generation category.
• library_name: transformers, enabling the "how to use" widget and automatic code snippets.
• A direct link to the GitHub repository.
• Corrects the BibTeX citation to match the official paper title.

Please review and merge if these improvements are satisfactory.