Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
nyu-visionx
/
Cambrian-S-7B
like
5
Follow
VISIONx @ NYU
136
Image-to-Text
Transformers
Safetensors
nyu-visionx/VSI-590K
English
cambrian_qwen
text-generation
multimodal
video-understanding
spatial-reasoning
vision-language
Eval Results
arxiv:
2511.04670
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Cambrian-S-7B
/
merges.txt
Commit History
Upload folder using huggingface_hub
a5a7227
verified
ShushengYang
commited on
Nov 4
ShushengYang
commited on
