dongguanting

/

Qwen3-8B-AEPO-DeepSearch

like 0

This PR enhances the model card for dongguanting/Qwen3-14B-AEPO-DeepSearch by adding key metadata and comprehensive content:

• Adds pipeline_tag: robotics to categorize the model effectively as an agentic reinforcement learning model, improving discoverability on the Hub.
• Adds library_name: transformers as evidence from config.json ("architectures": ["Qwen3ForCausalLM"], "transformers_version": "4.51.3") confirms compatibility with the 🤗 Transformers library.
• Updates the content to include the full paper title, a link to the Hugging Face paper page, and the complete paper abstract.
• Adds a link to the official GitHub repository for easy access to the codebase and project details.

No sample usage section is included as per the instructions, as no explicit code snippet was found in the provided GitHub README.