Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Mantis-VL
/
videollava-7b-video-eval-20k_2048
like
0
Follow
Mantis VL community
5
Transformers
Safetensors
video_llava
pretraining
Generated from Trainer
Inference Endpoints
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
videollava-7b-video-eval-20k_2048
File size: 61 Bytes
fec974e
1
2
3
4
5
6
{
"<image>"
:
32000
,
"<pad>"
:
32002
,
"<video>"
:
32001
}