Release Expert Merging artifacts on Hugging Face

[NielsRogge]

Hi @Littleor 🤗

Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and your paper "Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking" got featured on Hugging Face's paper page: https://huggingface.co/papers/2509.25712.
The paper page lets people discuss about your paper and find related artifacts (such as models, datasets, or demos). You can also claim the paper as yours, which will show up on your public profile at HF, and add GitHub and project page URLs.

I saw on your GitHub repository (https://github.com/Littleor/ExpertMerging) that the source code will be coming soon. That's great news! Once your code and any pre-trained models (e.g., merged models resulting from your method) or datasets (e.g., any specialized calibration data you might be releasing) are ready, it would be fantastic to make them available on the 🤗 Hub to improve their discoverability and visibility. We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.

Uploading models

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 leverage the hf_hub_download one-liner to download a checkpoint from the Hub.

We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.

Uploading dataset

Would be awesome to make the dataset available on 🤗 , so that people can do:

from datasets import load_dataset

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

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 or need any help regarding this once your artifacts are ready for release!

Cheers,

Niels
ML Engineer @ HF 🤗

[Littleor]

Thanks for the interest and suggestions! The code has been open-sourced in this repository—feedback is welcome. I’ll also consider uploading the model/weights to Hugging Face to make it easier to reproduce and use. However, due to compliance and other issues, it will need more time and we will consider this matter carefully, thanks again.