Unlocking Generative AI with Phi-3-mini: A Guide to Inference and Deployment

Discover how Phi-3-mini, a new series of models from Microsoft, enables deployment of Large Language Models (LLMs) on edge devices and IoT devices. Learn how to use Semantic Kernel, Ollama/LlamaEdge, and ONNX Runtime to access and infer Phi-3-mini models, and explore the possibilities of generative AI in various application scenarios.

Features

inference phi3-mini model in:

• Semantic Kernel
• Ollama
• LlamaEdge
• ONNX Runtime
• iOS

Getting Started

Prerequisites

• macOS/Windows/Liunx
• python 3.10+

Guideline

please read my blog https://aka.ms/phi3gettingstarted to run the demo

please read my blog and follow guildeline to run iPhone demo

Resources

• Phi-3 CookBook http://aka.ms/phi-3cookbook
• Phi-3 Azure blog https://aka.ms/phi3blog-april
• Phi-3 technical report https://aka.ms/phi3-tech-report
• Learn ONNX Runtime Generative AI https://github.com/microsoft/onnxruntime-genai
• Learn about Semantic Kernel https://aka.ms/SemanticKernel
• Read Semantic Kernel Cookbook https://aka.ms/SemanticKernelCookBook
• Learn about LlamaEdge https://github.com/LlamaEdge/LlamaEdge
• Learn about Ollama https://ollama.com/