Promote Sign in Sign up

Multimodal model

VLX-Seek-1.5-10B

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

omlab Multimodal Open weights apache-2.0
Open model card ↗
Type
Multimodal
Weights
Open
Downloads
139k
Likes
19
Pipeline
image text to text
License
apache-2.0

Model hub

omlab/VLX-Seek-1.5-10B

Repo
omlab/VLX-Seek-1.5-10B
Library
transformers
Access
Public
Technical tags and languages
zh en transformers safetensors vlx_seek_1_5 text-generation vlx object-detection grounding multimodal REC VLM zero-shot-object-detection image-text-to-text
Open on Hugging Face