🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-first applications

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

ms-swift: Use PEFT or Full-parameter to finetune 250+ LLMs or 35+ MLLMs. (Qwen2, GLM4, Internlm2, Yi, Llama3, Llava, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

Android RSS reader app

Very fast synchronous and asynchronous C++17 logging library

A Progressive Web App for local file sharing

A cross-platform, reimplementation of Notepad++

中文的C++ Template的教学指南。与知名书籍C++ Templates不同，该系列教程将C++ Templates作为一门图灵完备的语言来讲授，以求帮助读者对Meta-Programming融会贯通。(正在施工中)

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

Agent framework and applications built upon Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

AI chat for every model.

BionicGPT is an on-premise replacement for ChatGPT, offering the advantages of Generative AI while maintaining strict data confidentiality

A Gradio web UI for Large Language Models.

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

A curated list of engineering blogs

🐚 OpenDevin: Code Less, Make More

🧡 Everything is RSSible

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

A computer science textbook

RAG AutoML Tool - Find optimal RAG pipeline for your own data.

The SuperC Parsing Framework

20+ high-performance LLM implementations with recipes to pretrain, finetune and deploy at scale.

Training LLMs with QLoRA + FSDP

A deep dive into embeddings starting from fundamentals

线性代数：未竟之美

Easy, fast, and cheap pretrain,finetune, serving for everyone

lightweight, standalone C++ inference engine for Google's Gemma models.