Release Graph-R1 artifacts (models and Knowledge HyperGraphs) on Hugging Face

[NielsRogge]

Hi @LHRLAB 🤗

Niels here from the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2507.21892.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo for instance), you can also claim
the paper as yours which will show up on your public profile at HF, add Github and project page URLs.

It'd be great to make the checkpoints and dataset available on the 🤗 hub, to improve their discoverability/visibility.
We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.

Uploading models

I saw the training scripts for Graph-R1 in your repository. Would you be open to hosting the pre-trained RL-tuned checkpoints (such as the Qwen2.5-3B-Instruct variant) on Hugging Face?

See here for a guide: https://huggingface.co/docs/hub/models-uploading.

In this case, we could leverage the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to any custom nn.Module. Alternatively, one can leverages the hf_hub_download one-liner to download a checkpoint from the hub.

Uploading dataset

I noticed you are currently using TeraBox to share your pre-built Knowledge HyperGraphs and processed datasets. It would be awesome to make these available on 🤗 , so that people can do:

from datasets import load_dataset

dataset = load_dataset("your-hf-org-or-username/graph-r1-hypergraphs")

See here for a guide: https://huggingface.co/docs/datasets/loading.

Besides that, there's the dataset viewer which allows people to quickly explore the first few rows of the data in the browser.

Let me know if you're interested/need any help regarding this!

Cheers,

Niels
ML Engineer @ HF 🤗