Release artifacts (models, dataset) on Hugging Face

[NielsRogge]

Hi @yake0409 🤗

Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv 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 your paper and 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.

It'd be great to make the checkpoints and the remaining datasets available on the 🤗 hub to improve their discoverability and visibility. I saw that you've already hosted the Audio-Visual-Text annotations at yake0409/MokA_AudioVisualText—that's a great start!

Uploading models

I noticed in your GitHub news that the MokA checkpoints have been updated. Would you be interested in hosting these (e.g., the LoRA adapters) on https://huggingface.co/models?

Hosting on Hugging Face will give you more visibility and enable better discoverability. We can add tags in the model cards so that people find the models easier and link them directly to the paper page. Since MokA uses PEFT/LoRA, you can easily push the adapter weights. You can also leverage the hf_hub_download one-liner to download a checkpoint from the hub.

Uploading dataset

I see you're using Google Drive for the Visual-Text training JSON. It would be awesome to make that dataset available on 🤗 as well, so that people can do:

from datasets import load_dataset

dataset = load_dataset("yake0409/moka-visual-text")

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 data in the browser.

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

Cheers,

Niels
ML Engineer @ HF 🤗