Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
TIGER-Lab
/
VISTA-VideoLLaVA
like
0
Follow
TIGER-Lab
152
Video-Text-to-Text
Safetensors
video_llava
arxiv:
2412.00927
License:
mit
Model card
Files
Files and versions
Community
5972453
VISTA-VideoLLaVA
File size: 61 Bytes
dbd809d
1
2
3
4
5
6
{
"<image>"
:
32000
,
"<pad>"
:
32002
,
"<video>"
:
32001
}