hugpadhugpad

ByteDance-Seed / UI-TARS-2B-SFT

Vision2.4B2.2K41Updated Jan 25, 2025
Hugging Face

Downloads

2.2K

Likes

41

Last updated

Jan 25, 2025

License

apache-2.0

UI-TARS is a next-generation native GUI agent model designed to interact seamlessly with graphical user interfaces (GUIs) using human-like perception, reasoning, and action capabilities. Unlike traditional modular frameworks, UI-TARS integrates all key components—perception, r…

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • qwen2_vl
  • image-text-to-text
  • multimodal
  • gui
  • conversational

Technical specifications

Parameters2.4B
Librarytransformers
Languagesen
Licenseapache-2.0