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

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:

@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

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MengqiLei/hyper-align

Finetuned
Qwen/Qwen3-8B
Finetuned
(1625)
this model

Paper for MengqiLei/hyper-align