IDEA-FinAI

/

TouchstoneGPT-7B-Instruct

like 3

Follow

IDEA FinAI 17

This PR updates the model card for IDEA-FinAI/TouchstoneGPT-7B-Instruct to accurately reflect its association with the paper "Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval" and the corresponding RAG-Factory GitHub repository.

The update includes:

• Clarifying that this repository hosts a Qwen2-7B-Instruct based model that can be used within the Think-on-Graph 3.0 framework.
• Incorporating the abstract of the Think-on-Graph 3.0 paper.
• Adding links to the paper and the RAG-Factory GitHub repository.
• Integrating features, installation steps, and general usage examples from the RAG-Factory GitHub README to provide context for the framework.
• Retaining the existing transformers sample usage for TouchstoneGPT-7B-Instruct, explicitly stating how to use this specific model.
• Updating metadata with relevant tags such as retrieval-augmented-generation, rag, graph-neural-networks, and llm-reasoning, while preserving existing finance and text-generation-inference tags relevant to the model itself.
• Updating images and badges to link to the RAG-Factory project and the Think-on-Graph 3.0 paper.

Please review and merge this PR to ensure the model card comprehensively describes the model and its relation to the Think-on-Graph 3.0 framework.