Task
Image To Text
S
sbintuitions/sarashina2.2-vision-3b
Image To Text·sbintuitions· 1.7K· 19
Sarashina2.2-Vision-3B Sarashina2.2-Vision-3B is a Japanese Large Vision Language Model trained by SB Intuitions.
# pull & run locally
pip install mlforge-sdk && mlforge pull sbintuitions/sarashina2.2-vision-3b
pip install mlforge-sdk && mlforge pull sbintuitions/sarashina2.2-vision-3b
Model details
Provider
sbintuitions
Framework
transformers
Parameters
3.8B
Size
7.1 GB
License
mit
Downloads
1.7K
Likes
19
Paper
arXiv:2404.07824
Updated
2026-02-27
About sbintuitions/sarashina2.2-vision-3b
Sarashina2.2-Vision-3B Sarashina2.2-Vision-3B is a Japanese Large Vision Language Model trained by SB Intuitions.