metadata
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
Model Description
GLADOS-1 is the first computer-use (CUA) model post-trained using collective, crowd-sourced trajectories. Leveraging the enourmous PANGO dataset (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, inspired by the existing Qwen2VL finetuning series.
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.
📕 Release Blog | 🤗 Code | 🔧 Deployment (via UI-TARS) | 🖥️ Running on your own computer (via UI-TARS Desktop)
Citation
@misc{chakralabs2025glados-1,
author = {Chakra Labs},
title = {GLADOS-1},
url = {https://github.com/Chakra-Network/GLADOS-1},
year = {2025}
}