Streamlit — A faster way to build and share data apps.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Always know what to expect from your data.

Ready-to-run Docker images containing Jupyter applications

A library for efficient similarity search and clustering of dense vectors.

A game theoretic approach to explain the output of any machine learning model.

TensorFlow's Visualization Toolkit

Personal CRM. Remember everything about your friends, family and business relationships.

Uniform Manifold Approximation and Projection

Low-code framework for building custom LLMs, neural networks, and other AI models

Quickly and accurately render even the largest data.

A Flexible and Powerful Parameter Server for large-scale machine learning

Demonstrations of Magenta Models

Drop-in replacement for argparse with added support for config files and environment variables.

Perform data science on data that remains in someone else's server

Deep universal probabilistic programming with Python and PyTorch

Magenta: Music and Art Generation with Machine Intelligence

A Python toolbox for performing gradient-free optimization

PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

A cd command that learns - easily navigate directories from the command line

A List of Recommender Systems and Resources

🤖 GPU accelerated Neural networks in JavaScript for Browsers and Node.js

Python Implementation of Reinforcement Learning: An Introduction

Facilitating the design, comparison and sharing of deep text matching models.

PYBOSSA is the ultimate crowdsourcing framework (aka microtasking) to analyze or enrich data that can't be processed by machines alone.

Lime: Explaining the predictions of any machine learning classifier

TensorFlow code and pre-trained models for BERT

Open Source ML Model Versioning, Metadata, and Experiment Management

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

Magnificent app which corrects your previous console command.