TMLR-Group-HF

/

GT-Qwen3-8B-Base-DAPO14k

like 1

Follow

TMLR Group 20

This PR significantly enhances the model card for GT-GRPO: Qwen3-8B-Base trained on DAPO-14k by:

• Adding library_name: transformers to the metadata, enabling the automated "How to use" widget, as evidenced by config.json and tokenizer_config.json.
• Adding pipeline_tag: text-generation for better discoverability, as the model is a Causal LM for reasoning tasks.
• Incorporating a direct link to the research paper: Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models.
• Including a concise summary of the paper's abstract to provide essential context about the Co-rewarding framework.
• Updating the main title for clarity and adding a dedicated section for the GitHub repository.
• Adding the BibTeX citation provided in the project's GitHub README.

These changes improve the model's discoverability and provide users with comprehensive information for better understanding and usage.