A newer version of the Gradio SDK is available:
5.45.0
metadata
title: UITARS Grounding Model
emoji: 🐨
colorFrom: pink
colorTo: gray
sdk: gradio
sdk_version: 5.42.0
app_file: app.py
pinned: false
license: mit
short_description: A grounding model for CUA
UI-TARS Grounding Model
A grounding model for Computer Use Agents (CUA) that can understand screen elements and generate action plans.
Usage
- Upload a screenshot of your desktop/browser
- Describe what you want to do
- Get grounding results with element locations and action plans
Model
This space hosts the UI-TARS-1.5-7B model for visual grounding tasks.
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference