Machine Learning & Deep Learning Repositories

gym

by openai

Total Stargazers:37238

Total Subscribers:1038

A toolkit for developing and comparing reinforcement learning algorithms.

pytorch-image-models

by huggingface

Total Stargazers:37138

Total Subscribers:324

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

marked

by markedjs

Total Stargazers:37135

Total Subscribers:385

A markdown parser and compiler. Built for speed.

mediapipe

by google-ai-edge

Total Stargazers:36922

Total Subscribers:532

Cross-platform, customizable ML solutions for live and streaming media.

PDFMathTranslate

by PDFMathTranslate

Total Stargazers:36875

Total Subscribers:128

[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

HanLP

by hankcs

Total Stargazers:36489

Total Subscribers:1117

中文分词词性标注命名实体识别依存句法分析成分句法分析语义依存分析语义角色标注指代消解风格转换语义相似度新词发现关键词短语提取自动摘要文本分类聚类拼音简繁转换自然语言处理

jax

by jax-ml

Total Stargazers:36297

Total Subscribers:333

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

llmfit

by AlexsJones

Total Stargazers:36200

Total Subscribers:115

Hundreds of models & providers. One command to find what runs on your hardware.

sglang

by sgl-project

Total Stargazers:35850

Total Subscribers:182

SGLang is a high-performance serving framework for large language models and multimodal models.

frigate

by blakeblackshear

Total Stargazers:35783

Total Subscribers:257

NVR with realtime local object detection for IP cameras

OCRmyPDF

by ocrmypdf

Total Stargazers:34726

Total Subscribers:193

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

detectron2

by facebookresearch

Total Stargazers:34707

Total Subscribers:398

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

diffusers

by huggingface

Total Stargazers:34500

Total Subscribers:224

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

CLIP

by openai

Total Stargazers:34286

Total Subscribers:330

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

airllm

by lyogavin

Total Stargazers:34201

Total Subscribers:288

AirLLM 70B inference with single 4GB GPU

zxing

by zxing

Total Stargazers:34092

Total Subscribers:1655

ZXing ("Zebra Crossing") barcode scanning library for Java, Android

spaCy

by explosion

Total Stargazers:33893

Total Subscribers:564

💫 Industrial-strength Natural Language Processing (NLP) in Python

happy-llm

by datawhalechina

Total Stargazers:33720

Total Subscribers:105

📚 从零开始构建大模型

tinygrad

by tinygrad

Total Stargazers:33587

Total Subscribers:288

You like pytorch? You like micrograd? You love tinygrad! ❤️

netron

by lutzroeder

Total Stargazers:33475

Total Subscribers:327

Visualizer for neural network, deep learning and machine learning models

x-algorithm

by xai-org

Total Stargazers:33161

Total Subscribers:295

Algorithm powering the For You feed on X

numpy

by numpy

Total Stargazers:32726

Total Subscribers:606

The fundamental package for scientific computing with Python.

fish-speech

by fishaudio

Total Stargazers:32663

Total Subscribers:167

SOTA Open Source TTS

timesfm

by google-research

Total Stargazers:32318

Total Subscribers:211

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

fairseq

by facebookresearch

Total Stargazers:32229

Total Subscribers:425

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

rxjs

by ReactiveX

Total Stargazers:31696

Total Subscribers:448

A reactive programming library for JavaScript

pytorch-lightning

by Lightning-AI

Total Stargazers:31337

Total Subscribers:260

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

heretic

by p-e-w

Total Stargazers:31225

Total Subscribers:151

Fully automatic censorship removal for language models

llm.c

by karpathy

Total Stargazers:30983

Total Subscribers:301

LLM training in simple, raw C/CUDA

stanford_alpaca

by tatsu-lab

Total Stargazers:30244

Total Subscribers:343

Code and documentation to train Stanford's Alpaca models, and generate the data.

applied-ml

by eugeneyan

Total Stargazers:30125

Total Subscribers:963

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

EasyOCR

by JaidedAI

Total Stargazers:29987

Total Subscribers:333

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

genesis-world

by Genesis-Embodied-AI

Total Stargazers:29934

Total Subscribers:225

Simulation platform for general-purpose robotics & embodied AI learning.

insightface

by deepinsight

Total Stargazers:29713

Total Subscribers:527

State-of-the-art 2D and 3D Face Analysis Project

modular

by modular

Total Stargazers:29705

Total Subscribers:285

The Modular Platform (includes MAX & Mojo)

llama3

by meta-llama

Total Stargazers:29223

Total Subscribers:7

The official Meta Llama 3 GitHub site

Hands-On-Large-Language-Models

by HandsOnLLM

Total Stargazers:29045

Total Subscribers:295

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

nautilus_trader

by nautechsystems

Total Stargazers:28823

Total Subscribers:226

Production-grade Rust-native trading engine with deterministic event-driven architecture

xgboost

by dmlc

Total Stargazers:28754

Total Subscribers:886

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

spleeter

by deezer

Total Stargazers:28424

Total Subscribers:397

Deezer source separation library including pretrained models.

mlx

by ml-explore

Total Stargazers:28398

Total Subscribers:207

MLX: An array framework for Apple silicon

taichi

by taichi-dev

Total Stargazers:28369

Total Subscribers:392

Productive, portable, and performant GPU programming in Python.

label-studio

by HumanSignal

Total Stargazers:28252

Total Subscribers:188

Label Studio is a multi-type data labeling and annotation tool with standardized output format

cs249r_book

by harvard-edge

Total Stargazers:28192

Total Subscribers:218

Machine Learning Systems

fastai

by fastai

Total Stargazers:28133

Total Subscribers:618

The fastai deep learning library

mlflow

by mlflow

Total Stargazers:27920

Total Subscribers:325

The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

Qwen3

by QwenLM

Total Stargazers:27611

Total Subscribers:174

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

lerobot

by huggingface

Total Stargazers:27429

Total Subscribers:169

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

generative-models

by Stability-AI

Total Stargazers:27285

Total Subscribers:280

Generative Models by Stability AI

apollo

by ApolloAuto

Total Stargazers:26825

Total Subscribers:1097

An open autonomous driving platform

open-r1

by huggingface

Total Stargazers:26454

Total Subscribers:285

Fully open reproduction of DeepSeek-R1

deep-learning-for-image-processing

by WZMIAOMIAO

Total Stargazers:26374

Total Subscribers:170

deep learning for image processing including classification and object-detection etc.

MiniCPM-V

by OpenBMB

Total Stargazers:26362

Total Subscribers:166

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

pumpkin-book

by datawhalechina

Total Stargazers:26058

Total Subscribers:625

南瓜书：《机器学习》（西瓜书）公式详解

shap

by shap

Total Stargazers:25740

Total Subscribers:246

A game theoretic approach to explain the output of any machine learning model.

vit-pytorch

by lucidrains

Total Stargazers:25502

Total Subscribers:155

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

fastbook

by fastai

Total Stargazers:25286

Total Subscribers:523

The fastai book, published as Jupyter Notebooks

llm-action

by liguodongiot

Total Stargazers:25040

Total Subscribers:203

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

LLaVA

by haotian-liu

Total Stargazers:25019

Total Subscribers:159

Machine Learning & Deep Learning

Model development: frameworks, training, research code and classic ML domains.

gym

by openai

A toolkit for developing and comparing reinforcement learning algorithms.

pytorch-image-models

by huggingface

marked

by markedjs

A markdown parser and compiler. Built for speed.

mediapipe

by google-ai-edge

Cross-platform, customizable ML solutions for live and streaming media.

PDFMathTranslate

by PDFMathTranslate

[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

HanLP

by hankcs

中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理

jax

by jax-ml

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

llmfit

by AlexsJones

Hundreds of models & providers. One command to find what runs on your hardware.

sglang

by sgl-project

SGLang is a high-performance serving framework for large language models and multimodal models.

frigate

by blakeblackshear

NVR with realtime local object detection for IP cameras

OCRmyPDF

by ocrmypdf

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

detectron2

by facebookresearch

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

diffusers

by huggingface

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

CLIP

by openai

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

airllm

by lyogavin

AirLLM 70B inference with single 4GB GPU

zxing

by zxing

ZXing ("Zebra Crossing") barcode scanning library for Java, Android

spaCy

by explosion

💫 Industrial-strength Natural Language Processing (NLP) in Python

happy-llm

by datawhalechina

📚 从零开始构建大模型

tinygrad

by tinygrad

You like pytorch? You like micrograd? You love tinygrad! ❤️

netron

by lutzroeder

Visualizer for neural network, deep learning and machine learning models

x-algorithm

by xai-org

Algorithm powering the For You feed on X

numpy

by numpy

The fundamental package for scientific computing with Python.

fish-speech

by fishaudio

SOTA Open Source TTS

timesfm

by google-research

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

fairseq

by facebookresearch

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

rxjs

by ReactiveX

A reactive programming library for JavaScript

pytorch-lightning

中文分词词性标注命名实体识别依存句法分析成分句法分析语义依存分析语义角色标注指代消解风格转换语义相似度新词发现关键词短语提取自动摘要文本分类聚类拼音简繁转换自然语言处理