🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Animation engine for explanatory math videos

⚡ A Fast, Extensible Progress Bar for Python and CLI

You like pytorch? You like micrograd? You love tinygrad! ❤️

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

An open-source NLP research library, built on PyTorch.

Hackable and optimized Transformers building blocks, supporting a composable construction.

XLNet: Generalized Autoregressive Pretraining for Language Understanding

OpenMMLab Pose Estimation Toolbox and Benchmark.

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Pseudo API for Google Trends

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

Simple and easily configurable grid world environments for reinforcement learning

Official implementation of "Implicit Neural Representations with Periodic Activation Functions"

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

Pre-trained ELMo Representations for Many Languages

Evaluation code for various unsupervised automated metrics for Natural Language Generation.

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.

Automatic fingering generator for piano scores

Minimal Seq2Seq model with Attention for Neural Machine Translation in PyTorch

Minimalist NMT for educational purposes

10k crowdsourced images for training segnets

Neural Machine Translation with Keras

Implementation of https://srush.github.io/annotated-s4

a toolkit for pose estimation using deep learning

code for training the models from the paper "Learning Individual Styles of Conversational Gestures"

Research code for pixel-based encoders of language (PIXEL)