Minimalistic large language model 3D-parallelism training

A playbook for systematically maximizing the performance of deep learning models.

Compiler for LightGBM gradient-boosted trees, based on LLVM. Speeds up prediction by ≥10x.

Header-only C++/python library for fast approximate nearest neighbors

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

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

Implementation for "AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification"

X-Transformer: Taming Pretrained Transformers for eXtreme Multi-label Text Classification

ML Collections is a library of Python Collections designed for ML use cases.

Implementation of SiameseXML (ICML 2021)

Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"

DALL·E Mini - Generate images from a text prompt

😎 A curated list of awesome MLOps tools

The code for the prize winners in DrivenData competitions.

Google play scraper for Python inspired by <facundoolano/google-play-scraper>

The Open Source Feature Store for Machine Learning

📋 Survey papers summarizing advances in deep learning, NLP, CV, graphs, reinforcement learning, recommendations, graphs, etc.

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

🥶Vilio: State-of-the-art VL models in PyTorch & PaddlePaddle

🖥 Control your display's brightness & volume on your Mac as if it was a native Apple Display. Use Apple Keyboard keys or custom shortcuts. Shows the native macOS OSDs.

Shuffle every song in existence from YouTube

Data science interview questions and answers

Google Brain AutoML

Full Stack Deep Learning Online Course

A library for transfer learning by reusing parts of TensorFlow models.

A prize winning solution for DFDC challenge

Fast and Accurate ML in 3 Lines of Code

Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"