Trending Projects

Swin-Unet is a pure transformer-based model for medical image segmentation, with potential use in AI-powered coding tools.

A strong baseline and bag of tricks for deep person re-identification in computer vision.

A comprehensive collection of resources for model quantization research and optimization.

An extensible deep learning library that leverages JAX for high-performance ML research and production use cases.

An original implementation of SELF-RAG, a technique for learning to retrieve, generate, and critique through self-reflection.

Run Mixtral-8x7B language models on Colab or consumer desktops with offloading capabilities.

This repository provides a tutorial and code for implementing the YOLO v3 object detection algorithm from scratch using PyTorch.

An imbalanced dataset sampler for PyTorch that oversamples low-frequency classes and undersamples high-frequency ones.

TengineKit is a fast and easy-to-use SDK for real-time face detection, face landmarks, face attributes, hand detection, body detection, and more on mobile devices.

A JavaScript library that enables AI agents to recursively reason and argue with themselves to generate more coherent responses.

A fast and simple implementation of learning algorithms for robotics in Python.

This is an older version of the H2O open-source machine learning platform, please use the latest version at h2o-3.

A GUI tool for image upscaling using the ESRGAN deep learning model.

Implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference, for AI coding tools.

Tacotron-2 is a state-of-the-art text-to-speech model that vibe coders can use to build speech synthesis applications.

Tangent is a Python library for source-to-source debuggable automatic differentiation.

A Python library for dense prediction transformers, a type of neural network architecture for computer vision and language tasks.

A curated collection of ICCV conference papers, code, and interpretations for computer vision developers.

FastAPI wrapper for Grok AI with streaming, image generation, and load balancing

Instill Core is an open-source AI infrastructure tool for orchestrating data, models, and pipelines to build AI-powered applications.

PyRobot is an open-source robotics research platform for building and testing robotic applications.

A simple, powerful, and efficient API for building deep learning models in Python.

A Python library for fine-tuning large language models (LLMs) without fine-tuning the entire model.

A reverse-engineered Python API for interacting with the Google Gemini web app, a generative AI tool.

This is an open-source implementation of a multimodal instruction-based editing and generation model.

An open-source platform for AI engineering with LLM observability, GPU monitoring, and prompt management tools.

An open-source tutorial that helps developers deploy large language models (LLMs) like Ollama on CPU for production use.

Fully open data curation for reasoning models for vibe coders building with AI tools.

Export and share your ChatGPT conversation history as Markdown files.

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

A curated list of awesome papers and resources for building recommender systems using large language models (LLM).

A fast and robust C++ library for 3D point cloud registration, useful for robotics and SLAM applications.

A Swift library for chatting with private and local large language models on iOS devices.

AxonHub is a Go-based AI gateway system that provides a unified API for OpenAI, Anthropic, Gemini, and other AI SDKs.

Turn any computer or edge device into a command center for your computer vision projects.

Turing.jl is a powerful Bayesian inference library for probabilistic programming in the Julia language.

An open-source library for deep learning on satellite and aerial imagery using Python and PyTorch.

Open-source Python library for feature engineering and selection, compatible with scikit-learn.

A video foundation model and dataset for multimodal understanding and video understanding tasks.

A PyTorch implementation of VALL-E, a zero-shot text-to-speech model for vibe coders.

Official implementation of EAGLE, a framework for developing AI-powered coding tools and language models.

A curated list of awesome resources about LLM-powered agents, including papers, repos, and blogs.

An AI-powered speech denoising and enhancement library for improving audio quality.

GLIGEN is an open-source library for grounded text-to-image generation, enabling developers to create AI-powered image generation models.

A PyTorch implementation of various Unet models for image segmentation, including Attention Unet and Nested Unet.

A scalable multimodal reasoning framework for AI-powered applications with a focus on video and image understanding.

Optax is a gradient processing and optimization library for JAX, a high-performance machine learning framework.

A powerful BERT-based language model for natural language understanding and representation learning.

Code for a paper on pointer-generator networks for text summarization.

NVIDIA's CUDA Core Compute Libraries for accelerated computing and GPU programming in C++