---
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
  - graph
  - text-rich-graph
  - message-passing
---

# Model Details

[RAMP](https://arxiv.org/abs/2603.14937) (Raw-text Anchored Message Passing) recasts the LLM as a graph-native aggregation operator on text-rich graphs. This checkpoint is pretrained with 2 message passing layers and compression ratio 0.1.

- **Base model:** Qwen2.5-7B-Instruct
- **Message passing layers:** 2
- **Compression ratio:** 0.1

For training, evaluation, and usage details, see our [GitHub repo](https://github.com/codefuse-ai/CodeFuse-RAMP).

# Citation

```bibtex
@article{zhang2026llm,
  title={LLM as Graph Kernel: Rethinking Message Passing on Text-Rich Graphs},
  author={Zhang, Ying and Yu, Hang and Zhang, Haipeng and Di, Peng},
  journal={arXiv preprint arXiv:2603.14937},
  year={2026}
}
```

[![Paper](https://img.shields.io/badge/arXiv-2603.14937-b31b1b.svg)](https://arxiv.org/abs/2603.14937)