OpenSPG

/

KAG-Thinker-en-ch-7b-instruct

like 4

Follow

Semantic-enhanced Programmable Graph 12

This PR adds a comprehensive model card for the Thinker model, improving its discoverability and usefulness on the Hugging Face Hub.

The updates include:

• Adding the pipeline_tag: text-generation and library_name: transformers to the model card metadata, ensuring proper integration with Hub features and automated usage examples.
• Providing a link to the official paper: Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction.
• Including the paper's abstract to give users an immediate understanding of the model's purpose and methodology.
• Linking to the official GitHub repository (https://github.com/OpenSPG/KAG-Thinker) for further details on installation, training, and advanced inference.
• Adding the BibTeX citation for proper academic attribution.

These changes make the model card more informative and user-friendly.