Promote Sign in Sign up

Multimodal model

UI-TARS-1.5-7B

Listed for image text to text. Explore the model card for usage and requirements.

ByteDance-Seed Multimodal Open weights apache-2.0
Open model card ↗
Type
Multimodal
Weights
Open
Downloads
595k
Likes
607
Pipeline
image text to text
License
apache-2.0

Model hub

ByteDance-Seed/UI-TARS-1.5-7B

Repo
ByteDance-Seed/UI-TARS-1.5-7B
Library
transformers
Access
Public
Technical tags and languages
en transformers safetensors qwen2_5_vl image-text-to-text multimodal gui conversational eval-results text-generation-inference endpoints_compatible
Open on Hugging Face

Papers

8