TMLR-Group-HF

/

Entropy-Qwen3-4B-Base-DAPO14k

like 0

Follow

TMLR Group 20

This PR enhances the model card by:

• Adding pipeline_tag: text-generation to correctly classify the model's functionality and improve discoverability on the Hub.
• Adding library_name: transformers as the config.json explicitly indicates transformers_version and Qwen3ForCausalLM architecture, enabling the automated "Use in Transformers" code snippet.
• Integrating the paper link: Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models to provide full academic context.
• Expanding the model description with a summary of the paper's abstract for better understanding.
• Reformatting the existing GitHub repository link for clarity.

These changes significantly improve the model card's informativeness and integration with the Hugging Face Hub features.