README.md

---
library_name: transformers
tags:
- multimodal
- gui
license: apache-2.0
datasets:
- chakra-labs/pango
- chakra-labs/pango-sample
language:
- en
base_model:
- ByteDance-Seed/UI-TARS-7B-SFT
pipeline_tag: image-text-to-text
---

# GLADOS-1 — UI-TARS-7B-SFT
![image/png](https://cdn-uploads.huggingface.co/production/uploads/66f5e39d1931d2d4817ab43c/ZGtCgRLXBQQbNMPJVLERW.png)

### Model Description
GLADOS-1 is the first computer-use (CUA) model post-trained using **collective, crowd-sourced trajectories**. 
Leveraging the enourmous [PANGO dataset](https://huggingface.co/datasets/chakra-labs/pango-sample) (with primarily Chrome based interactions), it's purpose is to provide a lense as to what's possible with enormous trajectory sizes in computer use.

It also represents the first open-sourced post-training pipeline for [UI-TARS](https://arxiv.org/pdf/2501.12326), inspired by the existing [Qwen2VL finetuning series](https://github.com/2U1/Qwen2-VL-Finetune).

This model is designed to: 
- **Be compliant**. It has been taught to rigorouly follow directions and output action formats compatible with downstream parsers like PyAutoGUI.
- **Understand web productivity applications**. The Pango dataset primarily contains productivity application usage in browser. Consequently in OSWorld results, we observe significantly improved performance on the Chrome task bench. 
- **Have strong intuition on visual grounding**. Our experiments are detailed more closely here in our [research blog](TBD).


<div align="left">
<p>
        📕 <a href="https://www.chakra.dev/research/glados-1-compute-use-model-crowdsourced-trajectories">Release Blog</a>&nbsp&nbsp | &nbsp&nbsp 🤗 <a href="https://github.com/Chakra-Network/GLADOS-1">Code</a>&nbsp&nbsp 
        | &nbsp&nbsp 🔧 <a href="https://github.com/bytedance/UI-TARS/blob/main/README_deploy.md">Deployment (via UI-TARS)</a> &nbsp&nbsp  | &nbsp&nbsp
🖥️ <a href="https://github.com/bytedance/UI-TARS-desktop">Running on your own computer (via UI-TARS Desktop)</a>&nbsp&nbsp
</p>
</div>

## Citation

```tex
@misc{chakralabs2025glados-1,
  author = {Chakra Labs},
  title = {GLADOS-1},
  url = {https://github.com/Chakra-Network/GLADOS-1},
  year = {2025}
}
```