Microsoft has introduced Phi-3-vision, a small language model capable of analyzing images and text, at the Microsoft Build 2024 conference.
Phi-3-vision has 4.2 billion parameters and can perform visual reasoning tasks like analyzing graphs or images and responding to related queries.
The company claims that the model is cost-effective and requires less computational capacity suitable for mobile devices
Phi-3 series models (Phi-3-mini, Phi-3-small, and Phi-3-medium) are available in Microsoft Azure and Phi-3-vision is available on preview.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.