TMLR-Group-HF

/

GT-Qwen3-8B-Base-MATH

like 2

Follow

TMLR Group 17

This PR improves the model card for TMLR-Group-HF/GT-Qwen3-8B-Base by:

• Adding the library_name: transformers metadata tag, enabling the automated "how to use" widget on the model page, as indicated by the model's architecture (Qwen3ForCausalLM).
• Adding the pipeline_tag: text-generation metadata tag, which helps users discover the model when filtering for text generation models on the Hub, consistent with its function as an LLM for reasoning.
• Including a direct link to the paper (Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models) in the model description for easy access to the research.
• Correcting the project name from "Co-Reward" to "Co-rewarding" in the model description and GitHub repository link for consistency with the paper and GitHub repository.
• Updating the BibTeX citation to match the official citation provided in the paper's GitHub README, including the accurate title and author list, and correcting the year formatting.

Please review and merge this PR if everything looks good.