---
license: apache-2.0
library_name: transformers
base_model: Qwen/Qwen3-8B
tags:
  - hypergraph
  - large-language-models
  - qwen3
  - projector
  - hyper-align
  - hypergraph-as-language
  - arxiv:2605.21858
inference: false
---

# Hyper-Align

This repository contains the released **Hyper-Align** projector checkpoint for the paper **Hypergraph as Language**.

Hyper-Align is a hypergraph-native alignment framework that makes high-order association structures directly consumable by a frozen large language model. This checkpoint uses the **HIDT-O** hypergraph serialization protocol and the **HIP** projector to map hypergraph incidence information into the token space of **Qwen/Qwen3-8B**.

> This repository does not include the base LLM or text encoder weights. Users must download those models from their official Hugging Face repositories.

## Files

```text
config.json
mm_projector.bin
```

- `config.json` defines the Hyper-Align wrapper and HIP projector configuration.
- `mm_projector.bin` contains the trained projector weights.

Keep both files in the same checkpoint directory. The evaluation code uses `config.json` to instantiate the Hyper-Align model wrapper and projector before loading `mm_projector.bin`.

## License

The Hyper-Align code and released projector checkpoint are distributed under the Apache License 2.0.

The base LLM and embedding model are not redistributed here. Users must comply with the licenses and terms of the corresponding upstream model repositories:

- `Qwen/Qwen3-8B`
- `Qwen/Qwen3-Embedding-0.6B`

## Citation

If you use this checkpoint, please cite:

```bibtex
@article{lei2026hypergraph,
  title={Hypergraph as Language},
  author={Lei, Mengqi and Xie, Guohuan and Ying, Shihui and Du, Shaoyi and Yong, Jun-Hai and Li, Siqi and Gao, Yue},
  journal={arXiv preprint arXiv:2605.21858},
  year={2026}
}
```

## Links

- Paper: https://arxiv.org/abs/2605.21858
- Code: https://github.com/Mengqi-Lei/Hypergraph-as-Language