Explore Projects
Discover 3,069 open source projects
Showing 2941-2960 of 3,069 projects
pbloem/former
A simple PyTorch implementation of the Transformer model, useful for AI/ML developers.
TheAiSingularity/graphrag-local-ollama
Local support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3) - LLM & Embedding extraction
welkinwong/nodercms
A lightweight CMS built with Node.js and MongoDB, offering a flexible content model and robust permission management.
doctyper/flexie
A JavaScript library that provides legacy support for the CSS3 Flexible Box Model.
ray-project/llmperf
A library for validating and benchmarking large language models (LLMs) for developers working with AI tools.
Tencent/TencentPretrain
Tencent Pre-training framework in PyTorch with a pre-trained model zoo for NLP tasks
nari-labs/dia2
A real-time text-to-speech model that can stream conversational audio in real-time.
ibayer/fastFM
A fast, scalable library for Factorization Machines, a powerful machine learning model for recommendation systems.
ShareGPT4Omni/ShareGPT4Video
An official implementation of a system for improving video understanding and generation with better captions.
mit-han-lab/tinyml
This is a library for running TinyML (Tiny Machine Learning) models on low-power devices like microcontrollers.
ethanhe42/channel-pruning
A library for accelerating deep neural networks through channel pruning, a model compression technique.
icerockdev/moko-mvvm
MOKO MVVM is a set of Kotlin Multiplatform components for building MVVM-based mobile apps for Android and iOS.
TonnyL/Espresso
Espresso is an express delivery tracking app built with Material Design, MVP architecture, and popular libraries.
rixwew/pytorch-fm
A PyTorch library for building Factorization Machine models for click-through rate prediction tasks.
sfzhang15/ATSS
An object detection framework that bridges the gap between anchor-based and anchor-free detection models.
rykov8/ssd_keras
A Keras port of the Single Shot MultiBox Detector (SSD) for object detection in computer vision.
fpgaminer/joycaption
JoyCaption is an open, uncensored image captioning Visual Language Model (VLM) for training Diffusion models.
OpenGVLab/VideoMamba
VideoMamba is a state space model for efficient video understanding, focused on AI and machine learning.
IDEA-Research/Grounding-DINO-1.5-API
A powerful open-world object detection model for computer vision tasks, leveraging the DINO framework.
dgreenheck/OpenFracture
Open source mesh slicing/fracturing utility for Unity developers working with 3D models and simulations.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.