Release DiffAtlas artifacts (models, dataset) on Hugging Face

[NielsRogge]

Hi @M3DV 🤗

Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv related to DiffAtlas and was wondering whether you would like to submit it to hf.co/papers to improve its discoverability. If you are one of the authors, you can submit it at https://huggingface.co/papers/submit.

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, and add Github and project page URLs.

I noticed your Github repository, but I'm unsure whether you plan to release any pre-trained model checkpoints or datasets associated with DiffAtlas. If you do, it would be fantastic to host them on the 🤗 Hub (huggingface.co) to significantly improve their discoverability and visibility. We can add tags so that people find them easily when filtering models and datasets.

For models, see our guide here: https://huggingface.co/docs/hub/models-uploading. We recommend using the PyTorchModelHubMixin if you're working with PyTorch, which simplifies uploading with push_to_hub. Users can then easily download with from_pretrained.

For datasets, check out: https://huggingface.co/docs/datasets/loading. This allows users to load your data directly into their projects using the datasets library:

from datasets import load_dataset

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

The Hub also features a dataset viewer, enabling quick exploration of the data in the browser.

Please let me know your plans regarding artifact release. I'm happy to help with the process and link the released artifacts to your paper on the Hub.

Cheers,

Niels
ML Engineer @ HF 🤗