Release SparseVideoNav artifacts (models, dataset) on Hugging Face

Comienza con los detalles de la versión planificada en el GitHub README y con las guías enlazadas para subir modelos y conjuntos de datos a Hugging Face. Se considera terminado cuando los checkpoints del modelo SparseVideoNav y el conjunto de datos VLN de 140 horas del mundo real estén publicados en Hugging Face en repositorios independientes y fáciles de descubrir, con instrucciones de carga utilizables.

Hi @stdcat 🤗

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/2602.05827.
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.

I saw in your GitHub README that you plan to release the SparseVideoNav model checkpoints (distilled video generation and action head) and the 140h real-world VLN dataset later this year. It'd be great to make these available on the 🤗 hub when you release them, 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, for your video generation or action models, you 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.

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 140h 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 when you get closer to your release dates!

Cheers,

Niels
ML Engineer @ HF 🤗