Phi 3 vision
Phi-3-Vision is Microsoft’s compact, open-weight multimodal model that understands images + text and answers in text. Optimized for documents, charts, UI screenshots, diagrams, and photos, it delivers strong OCR and visual reasoning in a small footprint suitable for single-GPU or edge deployment.
- Type
- Text
- Weights
- Open
- Downloads
- 68k
- Likes
- 973
- Pipeline
- text generation
- License
- mit
Model hub
microsoft/Phi-3-vision-128k-instruct
- Repo
- microsoft/Phi-3-vision-128k-instruct
- Library
- transformers
- Access
- Public
Technical tags and languages
More from Gentext Group
7
About Gentext Group
1
Write research papers faster and smarter with our AI-powered MS Word Add-in. Leverage a database of 200 million+ peer reviewed articles.
Tools using Phi 3 vision
5