sagar007
multigemma
Tags
- multimodal
- vision-language
- gemma
- clip
- llava
- pytorch
- lightning
- en
- dataset:liuhaotian/LLaVA-Instruct-150K
- arxiv:2304.08485
- arxiv:2403.08295
- license:apache-2.0
Languages
en
- Author
- sagar007
- Task
- image-to-text
- License
- apache-2.0
- Downloads
- 0
- Likes
- 0
- Access
- Gated