Release UI-TARS-1.5 and UI-TARS-2 models on Hugging Face
- Dominant language
- Python
- Stars
- 11.5k
- Forks
- 877
- PR merge metrics
- No merged PRs in 30d
Description
Hi @lovesnowbest 🤗
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/2509.02544.
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.
I noticed in your GitHub README for the `ui-tars` project (https://github.com/bytedance/ui-tars) that you are offering "early research access" to your top-performing UI-TARS-1.5 model. This paper itself introduces UI-TARS-2, which shows even further improvements.
It'd be great to make these newer checkpoints (UI-TARS-1.5 and UI-TARS-2) available on the 🤗 hub to improve their discoverability and visibility, making them easily accessible to the broader research community. We can add tags so that people find them when filtering https://huggingface.co/models.
## Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
In this case, we could leverage the [PyTorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) class which adds `from_pretrained` and `push_to_hub` to any custom `nn.Module`. Alternatively, one can leverage the [hf_hub_download](https://huggingface.co/docs/huggingface_hub/en/guides/download#download-a-single-file) 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.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the UI-TARS README and the Hugging Face model-uploading guide linked in the issue, then review the PyTorchModelHubMixin and hf_hub_download options. Done means UI-TARS-1.5 and UI-TARS-2 checkpoints are available as separate Hugging Face model repositories with discoverability tags and links to the paper page.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface, python, pytorch
- Domain
- machine-learning, release
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100