xxwu

/

Agent-STAR-RL-3B

like 0

Hi! I'm Niels from the Hugging Face team.

This PR improves the model card for Agent-STAR-RL-3B by adding relevant metadata and documentation. It ensures the model is correctly categorized and links it to the original research paper, code repository, and training dataset.

Key changes:

• Added pipeline_tag: text-generation.
• Added library_name: transformers (verified by the model's configuration files).
• Linked the base_model (Qwen2.5-3B-Instruct).
• Included links to the paper and GitHub repository in the description.
• Added the BibTeX citation for proper attribution.