Trending Projects

A large-scale vision-language model for video understanding and generation.

A library for efficient weight quantization of large language models to accelerate inference on edge devices.

An extremely lightweight implementation of GPT-2 in NumPy, useful for vibe coders building AI-powered apps.

A Python framework for generating AI-powered PowerPoint presentations using large language models.

Common Voice is an open-source project to help teach machines how real people speak through crowdsourcing.

GLM (General Language Model) is a large language model framework for natural language processing tasks.

A library for developing neural operators using Fourier methods and PyTorch, enabling efficient learning on infinite dimensional spaces.

A text detection library using the CTPN model, supporting ID card detection and robust reading.

Image Restoration Toolbox with PyTorch-based training and testing codes for various AI-powered restoration models.

A collection of Jupyter Notebooks providing tutorials and examples for machine learning and deep learning using Python and PyTorch.

This repository provides the Chinese Simplified documentation for the TVM (Tensor Virtual Machine) framework, a popular open-source deep learning compiler stack.

A C++ library for audio and music analysis, description, and synthesis, with Python bindings.

An entropy-based sampling and parallel CoT decoding library for Python developers.

This GitHub repository provides AI and Machine Learning tutorials and examples using Kubeflow, Amazon EKS, and SageMaker.

An open machine learning course that covers a wide range of topics including computer vision, natural language processing, and reinforcement learning.

A Python library that enables editing of images using AI-powered tools like Segment Anything, ControlNet, and Stable Diffusion.

A Python library for generating photorealistic training images using the Blender 3D software.

Jiagu is a deep learning-based NLP toolkit that provides features like Chinese word segmentation, NER, sentiment analysis, and more.

A denoising autoencoder with adversarial losses and attention mechanisms for face swapping.

The fast.ai course notebooks, a resource for developers to learn deep learning and machine learning using the fastai library.

An open-source platform for game research and reinforcement learning experimentation.

An open-source toolbox for implementing state-of-the-art object detection models like YOLOv5, YOLOv6, YOLOv7, and RTMDet.

Modularized implementation of deep reinforcement learning algorithms in PyTorch for researchers and developers.

A Python tool for the Stable Diffusion WebUI that allows for the visualization of model differences.

A library of semantic segmentation architectures implemented in PyTorch for computer vision applications.

High-performance symbolic regression library for Python and Julia, with support for explainable AI.

A powerful graph embedding library for generating node embeddings from large-scale graph-structured data.

A Python library that provides reinforcement learning algorithms and environments for various card games

g2o is a C++ library for graph-based nonlinear optimization, primarily used in SLAM (Simultaneous Localization and Mapping) applications.

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

A Python package to easily retrain OpenAI's GPT-2 text-generation model on new texts.

Sample code for the Microsoft Cognitive Services Speech SDK, which allows developers to build voice-enabled applications.

LangChain is a framework for building applications with large language models (LLMs).

A platform for developers to integrate ChatGPT with a custom knowledge base using the OP Stack (OpenAI + Pinecone Vector Database)

PyTorch extensions for high performance and large scale training.

Improved AnimateDiff for ComfyUI and Advanced Sampling Support for AI-powered animation and image generation.

An open-source project that helps developers learn about large language models (LLMs), LLM operations, and vector databases for building real-time financial AI assistants.

An open-source AI wearable that transcribes and stores your conversations, enabling a personalized AI assistant.

.NET Standard bindings for Google's TensorFlow for developing, training and deploying Machine Learning models in C# and F#.

Baby Dragon Hatchling (BDH) is an AI-powered architecture and code repository for vibe coders.

A 3D computer vision framework for 3D reconstruction, camera tracking, and photogrammetry.

A Python library for automatic keyword extraction and text summarization from Chinese text using the TextRank algorithm.

A Python library for training and using Hidden Markov Models, with a scikit-learn-like API.

A comprehensive C++ library for motion planning and navigation of autonomous vehicles using ROS and various algorithms.

Photon is a Rust/WebAssembly image processing library for developers who want to leverage AI-powered image manipulation.

A PyTorch-based package of deep learning-based CTR models for easy-to-use, modular, and extendible development.

Open source platform to build a small-scale self-driving car using computer vision and AI.

An IDA plugin that uses language models to speed up reverse-engineering tasks for developers.

A collection of top solutions for various data competitions, useful for vibe coders working with AI tools.

Official codebase for developing cutting-edge computer vision models like Vision Transformer, SigLIP, and MLP-Mixer.