TMLR-Group-HF

/

GT-Qwen3-4B-Base-MATH

like 0

Follow

TMLR Group 20

This PR enhances the model card for TMLR-Group-HF/GT-Qwen3-4B-Base by:

• Adding pipeline_tag: text-generation to the metadata. This is appropriate for a Qwen3ForCausalLM model and improves discoverability on the Hugging Face Hub (e.g., at https://huggingface.co/models?pipeline_tag=text-generation).
• Adding library_name: transformers to the metadata. The config.json indicates compatibility with the transformers library, which enables the "how to use" widget on the model page for easy inference.
• Enriching the model description to include the paper title, a link to the official Hugging Face paper page (Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models), and a concise summary of the paper's abstract.
• Updating the GitHub repository link to https://github.com/tmlr-group/Co-rewarding to match the correct URL provided in the paper's GitHub README.

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