🔥 A collection of the newest Claude Code open source

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

Process Common Crawl data with Python and Spark

Demonstration of various hardware effects on CUDA GPUs.

Enabling PyTorch on XLA Devices (e.g. Google TPU)

PyTorch extensions for high performance and large scale training.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

shFlags is a port of the Google gflags library for Unix shell.

Code examples in pyTorch and Tensorflow for CS230

Unsupervised text tokenizer for Neural Network-based text generation.

Good Semi-Supervised Learning That Requires a Bad GAN

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

Reference implementation for "Neural Sequence Model Training via α-divergence Minimization"

Tutorial for building a custom CUDA function for Pytorch

Tools for PyTorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.

A language-agnostic interface to TensorBoard

Virtual adversarial training with Tensorflow

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy https://visdom.dev

Weight initialization schemes for PyTorch nn.Modules

Variational and semi-supervised neural network toppings for Lasagne

Deep generative models for semi-supervised learning.

Code for the paper "PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications"

Code for NLTK3 Cookbook

Train NLTK objects with zero code

Torch on steroids

A living collection of deep learning problems