TMLR-Group-HF

/

Self-Certainty-Qwen3-8B-Base-DAPO14k

like 1

Follow

TMLR Group 17

This PR updates the model card for the Self-Certainty: Qwen3-8B-Base trained on DAPO-14k model.

Key improvements include:

• Adding the pipeline_tag: text-generation to improve model discoverability on the Hub and enable the inference widget.
• Specifying library_name: transformers to allow for automated code snippets for easy usage with the Hugging Face Transformers library.
• Integrating the link to the original paper, Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models, providing crucial context for the model.