Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
configint
/
SmolVLM2-256M-Video-Instruct-Action
like
0
Follow
Config Intelligence
3
Image-Text-to-Text
Transformers
ONNX
Safetensors
12 datasets
English
smolvlm
image-to-text
conversational
arxiv:
2504.05299
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
SmolVLM2-256M-Video-Instruct-Action
File size: 67 Bytes
d4e497e
1
2
3
4
5
{
"image_seq_len"
:
64
,
"processor_class"
:
"SmolVLMProcessor"
}