Release VideoLISA on Hugging Face

[NielsRogge]

Hello @JosephPai 🤗

I'm Niels and work as part of the open-source team at Hugging Face. I discovered through AK's daily papers: https://huggingface.co/papers/2409.19603. The paper page lets people discuss about your paper and lets them find artifacts about it (your model for instance) you can also claim the paper as yours which will show up on your public profile at HF.

Would you like to host the model you've pre-trained on https://huggingface.co/models, enabling better visibility/discoverability of your work? We can add tags in the model cards so that people find the models easier, link it to the paper page, etc.

If you're down, leaving a guide here. If it's a PyTorch model, you can use PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to the model which lets you to upload the model and people to download and use models right away. If you do not want this and directly want to upload model through UI or however you want, people can also use hf_hub_download.

After uploaded, we can also link the models to the paper page (read here) so people can discover your model.

You can also build a demo to your model on Spaces we can provide you an A100 grant.

Kind regards,

Niels

[JosephPai]

Hi @NielsRogge, sorry for the late response as we were waiting for the internal approval of releasing the code. Now we released the code. The model is hosted at: https://huggingface.co/ZechenBai/VideoLISA-3.8B

[NielsRogge]

Awesome, the model card looks great!

I see the repository contains the "custom-code" tag, but there's no code present in the model repo.

If you push the modeling code to the repository, one could do this:

from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("ZechenBai/VideoLISA-3.8B", trust_remote_code=True)

See the guide here for more info on how to push code to the hub: https://huggingface.co/docs/transformers/custom_models.

Let me know if you need any help!