This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks

Azure AI Foundry (demos, documentation, accelerators).

Pivotal Token Search

Notolog Markdown Editor

A secure, on-device document analysis tool using Foundry Local & Microsoft Agent Framework

pRISM is a repository that combines Retrieval-Augmented Generation (RAG) with a multi-LLM voting approach to create accurate and reliable AI-generated outputs. It integrates multiple language models, including Mistral, Claude 3.5, and OpenAI, to enhance performance through advanced consensus techniques

🤖 Microsoft Phi-4 Multimodal Model Demo - A comprehensive Python application showcasing unified text, image, and audio processing with the 14B parameter Phi-4 multimodal model. Features 128K token context, 23+ language support, advanced reasoning capabilities, automated setup, GPU optimization, and real-time multimodal AI processing.

FlowerTune LLM on NLP Dataset

AWQ Quantization of Microsoft/Phi-4-Reasoning

Enhancing Fault Isolation in Hardware Systems Using Large Language Models (LLMs). Master's Degree Thesis developed in 2025.

odcvia 👁️‍🗨️👁️‍🗨️ : Object Detection # Obj-detection # CV # img-analysis # ai-vision

Run large language models locally using Ollama

🧠 Luna AI - Smart Coding Assistant A privacy-first, offline AI coding assistant powered by the Phi-4 model. Built with FastAPI and a modern web interface for intelligent code suggestions, debugging, and explanation — all running locally on your machine.

Review Analyzer is a fullstack AI-powered application that analyzes user-written product reviews using sentiment analysis and LLMs. It classifies reviews as accepted or rejected and provides personalized feedback and suggestions to help users improve their input before submission.