Release Byte Latent Transformer (BLT) on Hugging Face

[NielsRogge]

Hello @EntilZha 🤗 I'm Niels and work as part of 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/2412.09871.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance), you can also claim the paper as yours which will show up on your public profile at HF.
I see you are still working on updating the code. Once it is ready, would you like to host the model you've pre-trained on https://huggingface.co/models?
Hosting on Hugging Face will give you more visibility/enable better discoverability. 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 custom PyTorch model, you can use the 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 for your model on Spaces, we can provide you an A100 grant.

Let me know if you're interested/need any guidance :)

Kind regards,

Niels

[Tharun-tharun]

@EntilZha hoping the model weights are available soon on HuggingFace, can't wait to play with them. In between, this is a pretty good hot paper.

[kiratp]

Just getting the base model without any instruct tuning would be great! No need for all the accoutrements.

Just the amount of carbon emissions that would save from avoiding 100 companies all training their own copy!

[EntilZha]

Hi @NielsRogge @Tharun-tharun @kiratp, thanks for the interest in our model! Our team is very interested in releasing weights to facilitate adoption of BLT, but we don't currently have weights that we can release. If/when we do, we'd love to have your help getting things on HF. For timeline, most of us are away for holidays, so it will be at least a few weeks until we might have an update. Thanks again for the interest!