phi4-mini

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

Pivotal Token Search

Makes you feel less alone.

🔧Fine-tune Phi-4-mini-instruct model with LoRA on Azure Machine Learning Studio

A Telephonic Ai Agent,Listen-Think-Speak in Malayalam,Using Local LLM Stack

An ablation study adapting 4B-parameter LLMs (Qwen-2.5, Gemma-3, Phi-4) to the Indian Legal Domain. Features LoRA/QLoRA optimization, custom synthetic data generation, and an automated LLM-as-a-Judge evaluation pipeline.

How to Build a Local Agent

A local, privacy-preserving auto-grader built with LangGraph and Ollama. It evaluates student submissions against a JSON rubric using a pipeline of specialised agents, producing a structured Markdown feedback report.

Offline multimodal AI system with speech, vision, and language processing. LangGraph orchestration, Phi-4-mini LLM, Vosk STT, BLIP vision. Complete privacy, zero data transmission. Inspired by Interstellar's TARS.

A multitask framework for joint ASR and perceptual attribute analysis of dysarthric speech (ASRU 2025).

Lean local AI stack for low-end PCs (8 GB RAM, no GPU). Built on cc-haha + Ollama. Sub-ms routing, hallucination detection, zero cloud.

A lightweight, local-first system that decides per prompt whether a conversational AI needs earlier chat history to answer correctly, and fetches exactly the right slice of it when it does.

Optimized inference implementations for Microsoft's Phi-4-multimodal model. Supports text, image, and audio inputs with multiple inference strategies: standard (FP16), 4-bit quantized, and CPU-based approaches. Includes comprehensive benchmarks and deployment recommendations.

AI-powered outfit recommendation system using Phi-4-mini GGUF model. Generates personalized clothing suggestions based on body shape, style preferences, occasion, and location. Features multiple GGUF quantizations, GPU acceleration support, and structured JSON output with detailed styling tips.

An AI Agent to enable a "chat" with your QIF files.

RAG AI that uses Phi-4:3.8b Mini 4K and All-MiniLM locally

Self-hosted LLM security engine for SOC teams. Use any Ollama model to analyze threats, classify attacks, and score risk - fully offline, no cloud APIs, your data never leaves your network.

DejaFood é um projeto que envolve várias camadas de AI, desde a detecção e reconhecimento de alimentos por imagem, geração de receitas e busca na internet de receitas.

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