Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
nkkbr
/
ViCA2-stage1-align
like
0
Video-Text-to-Text
Transformers
Safetensors
sam2
liuhaotian/LLaVA-CC3M-Pretrain-595K
English
vica_qwen
text-generation
multimodal
vision-language
video understanding
visuospatial cognition
spatial reasoning
vlm
llava
qwen
siglip
hiera
dual-encoder
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
ViCA2-stage1-align
/
model-00004-of-00004.safetensors
Commit History
Initial commit
b1ee778
nkkbr
commited on
Apr 21
nkkbr
commited on
