cyberagent / llava-calm2-siglip
Vision7.5B14126Updated Jun 12, 2024
Downloads
141
Likes
26
Last updated
Jun 12, 2024
License
apache-2.0
llava-calm2-siglip is an experimental Vision Language Model that can answer questions in Japanese about images.
Tasks & library
- image to text
- transformers
Tags
- transformers
- llava
- image-text-to-text
- image-to-text
- ja
- en
Technical specifications
Parameters7.5B
Librarytransformers
Languagesja, en
Licenseapache-2.0