Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Supporting OpenAI GPT-OSS, IBM Granite-4, Qwen-3-VL, Gemma-3n, Ministral-3, and more.

Efficient Triton Kernels for LLM Training

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

An open-source project for Windows developers to learn how to add AI with local models and APIs to Windows apps.

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

Kolosal AI is an OpenSource and Lightweight alternative to LM Studio to run LLMs 100% offline on your device.

Phi3 中文后训练模型仓库

An open-source implementaion for fine-tuning Phi3-Vision and Phi3.5-Vision by Microsoft.

Chat effortlessly, execute commands, and interpret code with Llama3, Phi3, and more - your local AI assistant. Enjoy seamless interaction while ensuring ultimate privacy

Instruction/chat prompts creation library for text generation LLMs. It supports local and Hugging Face models.

Generative AI playground using Ollama, OpenAI API and JavaScript. Try AI models in your browser!

This project implements a web-based chatbot using open source technology

Scalable AI Inference Server for CPU and GPU with Node.js | Utilizes llama.cpp and parts of llamafile C/C++ core under the hood.

Transform your writing with TextLLaMA! ✍️🚀 Simplify grammar, translate effortlessly, and compose emails like a pro. 🌍📧

Sentiment analysis with pre-trained language models using TweetEval.

A RAG system is just the beginning of harnessing the power of LLM. The next step is creating an intelligent Agent. In Agentic RAG the Agent makes use of available tools, strategies and LLM to generate response in a specialized way. Unlike a simple RAG, an Agent can dynamically choose between tools, routing strategy, etc.

This experiment repository will be used for demonstration on using Phi-3.5, Microsoft's Small Language Model, locally with Ollama and JavaScript for the event of BKK.JS #21 and JavaScript Bangkok 2.0.0

A Chrome extension hosts an Ollama UI web server on localhost and other servers, helping you manage models and chat with any open-source model. 🚀💻✨

Sentinel is an AI agent that retrieves PubMed publications using phi3.5 with phidata to generate and run a MeSH search on NCBI Entrez.