Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Core deep-learning frameworks and libraries for pretraining and distributed training.
Signals: deep-learning, neural-network, pytorch, tensorflow, jax, distributed-training, training, deepspeed
2,672 results
Supervisely SDK for Python - convenient way to automate, customize and extend Supervisely Platform for your computer vision task
Clair3 - Symphonizing pileup and full-alignment for deep learning-based long-read variant calling
oneAPI Deep Neural Network Library (oneDNN)
Graph Neural Network Library for PyTorch
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
Neural Network primitives with multiple backends
Scientific machine learning (SciML) benchmarks, AI for science, and (differential) equation solvers. Covers Julia, Python (PyTorch, Jax), MATLAB, R
Data driven modeling and automated discovery of dynamical systems for the SciML Scientific Machine Learning organization
Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
A platform for reproducible world model research and evaluation
A zero-dependency ML framework in C with a modern Python API for full control over execution and memory.
High-performance automatic differentiation of LLVM and MLIR.
tfts: Time Series Deep Learning Models in TensorFlow
Flax is a neural network library for JAX that is designed for flexibility.
Magenta RealTime 2: An Open-Weights Live Music Model
A machine learning software for extracting information from scholarly documents
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.
🌊 Online machine learning in Python
PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.
Low-code framework for building custom LLMs, neural networks, and other AI models
Machine learning on FPGAs using HLS
推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/
Crater is a cloud-native AI training & inference platform.
Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.
24,540 repositories in the index in total.
