The absolute trainer to light up AI agents.

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

开源白板工具（SaaS），一体化白板，包含思维导图、流程图、自由画等。All in one open-source whiteboard tool with mind, flowchart, freehand and etc.

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

SoftVC VITS Singing Voice Conversion

Ongoing research training transformer models at scale

Heterogeneous AI Computing Virtualization Middleware(Project under CNCF)

SGLang is a fast serving framework for large language models and vision language models.

State-of-the-Art Text Embeddings

12 Lessons to Get Started Building AI Agents

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.

100-Days-Of-ML-Code中文版

12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

The official source code repository for the calibre ebook manager

Fully open reproduction of DeepSeek-R1

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Janus-Series: Unified Multimodal Understanding and Generation Models

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

A programming framework for agentic AI

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

BERT score for text generation

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.