Microsoft on its recent blog post confirmed that it will support developers to fine-tune Phi-3-mini and Phi-3-medium AI models on Azure to improve the performance of the models for different use cases.
For example, developers could fine-tune a Phi-3-medium model for tutoring students, or build a chat application tailored to a specific tone or response style.
The Phi-3-mini model was released in April this year, with a total of 3.8 billion parameters and two versions of context length: 4K and 128K; the Phi-3-medium model has a total of 14 billion parameters and two versions of context length: 4K and 128K.
