Open source. Open possibilities.

This project provides a large-scale Chinese NLP corpus with millions of high-quality entries, including Wikipedia, news, Q&A, and translation datasets, to support model pretraining and various NLP tasks.

A low-latency, modular voice-agent pipeline (VAD -> STT -> LLM -> TTS) that implements the OpenAI Realtime event set over WebSocket and WebRTC.

Official code repository for 'Build a Large Language Model (From Scratch)': step-by-step PyTorch implementation of GPT-like models, covering pretraining and finetuning with notebooks and exercises.

DocsGPT is an open-source AI platform for building intelligent agents and assistants, featuring document analysis, multi-model support, and enterprise search capabilities.

A tiny GPT language model (~540M parameters) designed to be trained from scratch on consumer laptop hardware, with pretraining on Fineweb-edu and chat finetuning capabilities.

Repomix packs an entire repository into a single AI-friendly file (XML, Markdown, JSON, or plain text) for feeding codebases into LLMs like Claude, ChatGPT, and Gemini. It offers token counting, security checks, code compression, and remote repository support.

An all-in-one AI framework for semantic search, LLM orchestration, and language model workflows.

Swift Tokenizers is a high-performance Swift wrapper around Hugging Face's Rust tokenizers crate, focused solely on tokenization without Hub dependencies. It supports macOS, iOS and Linux, offering encoding, decoding, streaming detokenization, chat templates and tool calling.

A free 21-lesson Microsoft course for beginners to build generative AI applications, covering LLMs, prompt engineering, RAG, agents, fine-tuning, and more, with Python/TypeScript examples.

GPT4Free aggregates multiple language model and media generation providers into a unified interface. It offers Python/JS clients, OpenAI-compatible REST API, GUI, and CLI. Supports text and image generation via various models including gpt-4o-mini and flux.

A comprehensive open-source guide covering prompt engineering techniques, RAG, AI agents, and LLM optimization. Includes tutorials, research papers, tools, and notebooks for working effectively with large language models.

ChatRWKV is an open-source chat interface powered by RWKV, a 100% RNN language model. It offers transformer-like quality with lower VRAM usage and faster inference. The project provides Python APIs, Gradio demos, and guides for fine-tuning and local deployment of RWKV models.