Edaizi

/

KG-TRACES

like 0

This PR significantly improves the model card for KG-TRACES by adding crucial metadata and essential documentation.

Key changes include:

• Metadata: Added pipeline_tag: text-generation to classify the model's primary function and library_name: transformers to indicate its compatibility with the Hugging Face Transformers library. Also added the relevant datasets (Edaizi/KG-TRACES-WebQSP, Edaizi/KG-TRACES-CWQ) for discoverability.
• Paper Link: Linked the model to its official paper: KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervision.
• Code Repository: Added a direct link to the GitHub repository for easy access to the code: https://github.com/Edaizi/KG-TRACES.
• Sample Usage: Included a Python code snippet to demonstrate how to load and use the model, directly sourced from the GitHub README.
• Descriptive Content: Incorporated an overview, key highlights, and dataset information from the paper abstract and GitHub README.
• Visuals: Embedded key images from the GitHub repository to enhance understanding.
• Citation: Added the BibTeX citation for proper attribution.

These additions will make the model more discoverable and user-friendly on the Hugging Face Hub.