TMLR-Group-HF

/

GT-Qwen3-8B-Base-OpenRS

like 1

Follow

TMLR Group 17

This PR improves the model card for the GT-GRPO: Qwen3-8B-Base trained on OpenRS model by:

• Adding 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 indicated by the model's config.json and transformers_version.
• Explicitly linking the model to its associated paper, Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models.
• Expanding the model description to provide more context about the model and its relation to the research presented in the paper.
• Adding the academic citation for the paper.