Open-source artifacts for InfantAgent-Next on Hugging Face

[NielsRogge]

Hi @bin123apple 🤗

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/2505.10887. I noticed your project, InfantAgent-Next, on Github.

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, add Github and project page URLs.

It would be fantastic if you considered hosting any pre-trained model checkpoints and/or datasets associated with InfantAgent-Next on the Hugging Face Hub. This would significantly improve the discoverability and accessibility of your research. We can help you with the process of uploading and tagging your artifacts.

We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.

For models, we could leverage the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to any custom nn.Module. Alternatively, one can use 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.

For datasets, having your datasets on Hugging Face would allow users to easily load them using from datasets import load_dataset. We also support WebDataset for image/video datasets and have a built-in dataset viewer.

Let me know if you're interested or have any questions. We're here to help!

Kind regards,

Niels
ML Engineer @ Hugging Face 🤗

[bin123apple]

Thank you for your interest and for Hugging Face’s 🤗 dedication to open source. Our current work is focused on the inference end; if we later train models built on this framework, we will share them on Hugging Face. Thank you.