Machine Learning & Deep Learning Repositories

tensorflow

by tensorflow

Total Stargazers:199738

Total Subscribers:7517

An Open Source Machine Learning Framework for Everyone

transformers

by huggingface

Total Stargazers:165201

Total Subscribers:1234

🤗 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.

whisper

by openai

Total Stargazers:108952

Total Subscribers:782

Robust Speech Recognition via Large-Scale Weak Supervision

LLMs-from-scratch

by rasbt

Total Stargazers:104842

Total Subscribers:852

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

DeepSeek-V3

by deepseek-ai

Total Stargazers:104434

Total Subscribers:746

______________

pytorch

by pytorch

Total Stargazers:102956

Total Subscribers:1802

Tensors and Dynamic neural networks in Python with strong GPU acceleration

autoresearch

by karpathy

Total Stargazers:95651

Total Subscribers:736

AI agents running research on single-GPU nanochat training automatically

DeepSeek-R1

by deepseek-ai

Total Stargazers:91994

Total Subscribers:602

______________

opencv

by opencv

Total Stargazers:90809

Total Subscribers:2611

Open Source Computer Vision Library

ML-For-Beginners

by microsoft

Total Stargazers:90411

Total Subscribers:1085

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

PaddleOCR

by PaddlePaddle

Total Stargazers:89391

Total Subscribers:566

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

llm-course

by mlabonne

Total Stargazers:82592

Total Subscribers:759

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

MinerU

by opendatalab

Total Stargazers:79771

Total Subscribers:283

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

models

by tensorflow

Total Stargazers:77661

Total Subscribers:2640

Models and examples built with TensorFlow

tesseract

by tesseract-ocr

Total Stargazers:76467

Total Subscribers:1715

Tesseract Open Source OCR Engine (main repository)

unsloth

by unslothai

Total Stargazers:76069

Total Subscribers:384

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

LlamaFactory

by hiyouga

Total Stargazers:74726

Total Subscribers:348

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

the-algorithm

by twitter

Total Stargazers:73903

Total Subscribers:413

Source code for the X Recommendation Algorithm

stable-diffusion

by CompVis

Total Stargazers:73417

Total Subscribers:571

A latent text-to-image diffusion model

Apollo-11

by chrislgarry

Total Stargazers:72334

Total Subscribers:1389

Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.

annotated_deep_learning_paper_implementations

by labmlai

Total Stargazers:67427

Total Subscribers:503

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

scikit-learn

by scikit-learn

Total Stargazers:67235

Total Subscribers:2131

scikit-learn: machine learning in Python

keras

by keras-team

Total Stargazers:64317

Total Subscribers:1853

Deep Learning for humans

openpilot

by commaai

Total Stargazers:63640

Total Subscribers:1323

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

nanoGPT

by karpathy

Total Stargazers:63030

Total Subscribers:540

The simplest, fastest repository for training/finetuning medium-sized GPTs.

ultralytics

by ultralytics

Total Stargazers:61536

Total Subscribers:268

Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

minimind

by jingyaogong

Total Stargazers:60825

Total Subscribers:274

🧠 Train a 64M-parameter LLM from scratch in just 2h!

Real-Time-Voice-Cloning

by CorentinJ

Total Stargazers:60127

Total Subscribers:937

Clone a voice in 5 seconds to generate arbitrary speech in real-time

llama

by meta-llama

Total Stargazers:59608

Total Subscribers:540

Inference code for Llama models

yolov5

by ultralytics

Total Stargazers:57998

Total Subscribers:381

Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

nanochat

by karpathy

Total Stargazers:57972

Total Subscribers:379

The best ChatGPT that $100 can buy.

faceswap

by deepfakes

Total Stargazers:57544

Total Subscribers:1526

Deepfakes Software For All

face_recognition

by ageitgey

Total Stargazers:56736

Total Subscribers:1541

The world's simplest facial recognition api for Python and the command line

segment-anything

by facebookresearch

Total Stargazers:54854

Total Subscribers:339

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

freqtrade

by freqtrade

Total Stargazers:54302

Total Subscribers:777

Free, open source crypto trading bot

grok-1

by xai-org

Total Stargazers:52208

Total Subscribers:654

Grok open release

supervision

by roboflow

Total Stargazers:49973

Total Subscribers:308

We write your reusable computer vision tools. 💜

Made-With-ML

by GokuMohandas

Total Stargazers:49464

Total Subscribers:1269

Learn how to develop, deploy and iterate on production-grade ML applications.

julia

by JuliaLang

Total Stargazers:49092

Total Subscribers:921

The Julia Programming Language

qlib

by microsoft

Total Stargazers:48502

Total Subscribers:507

Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.

RxJava

by ReactiveX

Total Stargazers:48206

Total Subscribers:2150

RxJava – Reactive Extensions for the JVM – a library for composing asynchronous and event-based programs using observable sequences for the Java VM.

Umi-OCR

by hiroi-sora

Total Stargazers:47266

Total Subscribers:232

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

airflow

by apache

Total Stargazers:46839

Total Subscribers:794

Apache Airflow - A platform to programmatically author, schedule, and monitor workflows

TTS

by coqui-ai

Total Stargazers:46003

Total Subscribers:344

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

vnpy

by vnpy

Total Stargazers:45350

Total Subscribers:1430

基于Python的开源量化交易平台开发框架

paperless-ngx

by paperless-ngx

Total Stargazers:45039

Total Subscribers:165

A community-supported supercharged document management system: scan, index and archive all your documents

spark

by apache

Total Stargazers:43983

Total Subscribers:1998

Apache Spark - A unified analytics engine for large-scale data processing

ray

by ray-project

Total Stargazers:43785

Total Subscribers:486

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

DeepSpeed

by deepspeedai

Total Stargazers:43100

Total Subscribers:359

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

BettaFish

by 666ghj

Total Stargazers:42203

Total Subscribers:233

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

ColossalAI

by hpcaitech

Total Stargazers:41438

Total Subscribers:381

Making large AI models cheaper, faster and more accessible

BitNet

by microsoft

Total Stargazers:40234

Total Subscribers:356

Official inference framework for 1-bit LLMs

photoprism

by photoprism

Total Stargazers:40186

Total Subscribers:319

AI-Powered Photos App 🌈💎✨

bert

by google-research

Total Stargazers:40042

Total Subscribers:7

TensorFlow code and pre-trained models for BERT

polars

by pola-rs

Total Stargazers:39715

Total Subscribers:221

Extremely fast Query Engine for DataFrames, written in Rust

marker

by datalab-to

Total Stargazers:39688

Total Subscribers:142

Convert PDF to markdown + JSON quickly with high accuracy

google-research

by google-research

Total Stargazers:38740

Total Subscribers:789

Google Research

tesseract.js

by naptha

Total Stargazers:38693

Total Subscribers:486

Pure Javascript OCR for more than 100 Languages 📖🎉🖥

Kronos

by shiyu-coder

Total Stargazers:38685

Total Subscribers:342

Kronos: A Foundation Model for the Language of Financial Markets

langextract

by google

Total Stargazers:38574

Total Subscribers:175

Machine Learning & Deep Learning

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

tensorflow

by tensorflow

An Open Source Machine Learning Framework for Everyone

transformers

by huggingface

🤗 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.

whisper

by openai

Robust Speech Recognition via Large-Scale Weak Supervision

LLMs-from-scratch

by rasbt

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

DeepSeek-V3

by deepseek-ai

______________

pytorch

by pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

autoresearch

by karpathy

AI agents running research on single-GPU nanochat training automatically

DeepSeek-R1

by deepseek-ai

______________

opencv

by opencv

Open Source Computer Vision Library

ML-For-Beginners

by microsoft

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

PaddleOCR

by PaddlePaddle

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

llm-course

by mlabonne

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

MinerU

by opendatalab

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

models

by tensorflow

Models and examples built with TensorFlow

tesseract

by tesseract-ocr

Tesseract Open Source OCR Engine (main repository)

unsloth

by unslothai

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

LlamaFactory

by hiyouga

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

the-algorithm

by twitter

Source code for the X Recommendation Algorithm

stable-diffusion

by CompVis

A latent text-to-image diffusion model

Apollo-11

by chrislgarry

Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.

annotated_deep_learning_paper_implementations

by labmlai

scikit-learn

by scikit-learn

scikit-learn: machine learning in Python

keras

by keras-team

Deep Learning for humans

openpilot

by commaai

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

nanoGPT

by karpathy

The simplest, fastest repository for training/finetuning medium-sized GPTs.

ultralytics

by ultralytics

Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

minimind