Projects

Jupyter Notebook 5,124 stars

ZheC/Realtime_Multi-Person_Pose_Estimation

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

JavaScript 5,118 stars

WorldFlowAI/everything-claude-code

Claude Code toolkit - agents, commands, skills, rules, and hooks for productive AI-assisted development

Overview: This repository contains a complete collection of Claude Code configurations, including agents, commands, skills, rules, and hooks, designed for productive AI-assisted development. Key features: - Agents - Commands - Skills - Rules - Hooks Tech stack: Node.js Why it matters: This repository provides a comprehensive set of Claude Code configurations that have been refined over 10+ months of use, making them suitable for real-world product development. Repository: WorldFlowAI/everything-claude-code GitHub stars: 4900 GitHub description: Claude Code toolkit - agents, commands, skills, rules, and hooks for productive AI-assisted development

Jupyter Notebook 5,118 stars

datawhalechina/tiny-universe

《大模型白盒子构建指南》：一个全手搓的Tiny-Universe

Python 5,118 stars

mangiucugna/json_repair

Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

Python 5,117 stars

humphd/have-fun-with-machine-learning

An absolute beginner's guide to Machine Learning and Image Classification with Neural Networks

Python 5,116 stars

lyst/lightfm

A Python implementation of LightFM, a hybrid recommendation algorithm.

Python 5,107 stars

chatopera/Synonyms

:herb: 中文近义词：聊天机器人，智能问答工具包

Overview: Synonyms 是一个用于中文自然语言处理和理解的工具包，提供多种任务的中文近义词解决方案，包括推荐算法、相似度计算、语义偏移、关键字提取、智能问答和自动摘要等。 Key features: - 提供中文近义词解决方案 - 支持多种任务，如推荐算法、相似度计算、语义偏移、关键字提取、智能问答和自动摘要 - 使用词向量和分词技术，提高文本处理的准确性和效率 - 支持多种编程语言，包括Python Tech stack: Synonyms 使用Python编写，依赖于词向量和分词技术。 Why it matters: Synonyms 是一个强大的工具包，适用于需要处理中文文本的各种应用场景，能够显著提高文本处理的准确性和效率，适用于自然语言处理和理解的各种任务。

Python 5,107 stars

pytorch/executorch

On-device AI across mobile, embedded and edge for PyTorch

Jupyter Notebook 5,106 stars

naganandy/graph-based-deep-learning-literature

links to conference publications in graph-based deep learning

TypeScript 5,097 stars

opencx-labs/copilot

Rust 5,083 stars

huggingface/text-embeddings-inference

A blazing fast inference solution for text embeddings models

TypeScript 5,080 stars

callstack/agent-device

Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.

Jupyter Notebook 5,069 stars

rasbt/python-machine-learning-book-3rd-edition

The "Python Machine Learning (3rd edition)" book code repository

Python 5,067 stars

AutoGPTQ/AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Overview: AutoGPTQ is an easy-to-use LLM quantization package that provides user-friendly APIs based on the GPTQ algorithm, focusing on weight-only quantization. Key features: - Support for various LLM models - Fast inference speed - Perplexity comparison metrics Tech stack: Python Why it matters: AutoGPTQ simplifies the process of quantizing large language models, making it accessible for developers and researchers without requiring deep technical knowledge.

MDX 5,065 stars

huggingface/deep-rl-class

This repo contains the Hugging Face Deep Reinforcement Learning Course.

Jupyter Notebook 5,054 stars

Nyandwi/machine_learning_complete

A comprehensive machine learning repository containing 30+ notebooks on different concepts, algorithms and techniques.

### Overview: This comprehensive repository contains 35 notebooks covering various aspects of machine learning, including Python programming, data manipulation, data analysis, data visualization, data cleaning, classical machine learning, computer vision, and natural language processing (NLP). ### Key Features: - **Python Programming**: Essential for data science and machine learning. - **NumPy**: Used for array or matrix operations. - **Pandas**: Simplifies data analysis and manipulation. - **Matplotlib**: A data visualization tool for creating static, animated, and interactive visualizations. - **Seaborn**: Built on top of Matplotlib for simple data visualization. - **Scikit-Learn**: Easy to use for classical machine learning models. - **TensorFlow and Keras**: Popular deep learning frameworks for building neural networks. ### Tech Stack: Python, NumPy, Pandas, Matplotlib, Seaborn, Scikit-Learn, TensorFlow, Keras ### Why It Matters: This repository serves as a valuable resource for anyone looking to learn and apply machine learning concepts in a practical, easy-to-understand manner. The notebooks are designed with the reader in mind, providing clear explanations and visuals to enhance understanding.

C++ 5,052 stars