mttk

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

datasets

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

gpt-3

GPT-3: Language Models are Few-Shot Learners

PRML

PRML algorithms implemented in Python

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

hyperopt

Distributed Asynchronous Hyperparameter Optimization in Python

arxiv-latex-cleaner

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

missing-semester

The Missing Semester of Your CS Education 📚

lit

The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

checklist

Beyond Accuracy: Behavioral Testing of NLP models with CheckList

mplcyberpunk

"Cyberpunk style" for matplotlib plots

Fantasy-Premier-League

Creates a .csv file of all players in the English Player League with their respective team and total fantasy points

YouTokenToMe

Unsupervised text tokenizer focused on computational efficiency

bootiso

A bash program to securely create a bootable USB device from one image file.

geotorch

Constrained optimization toolkit for PyTorch

pytorch_block_sparse

Fast Block Sparse Matrices for Pytorch

Mini-Conf

Run a conference from your backyard.

entmax

The entmax mapping and its loss, a family of sparse softmax alternatives.

sparse_learning

Sparse learning library and sparse momentum resources.

text-autoencoders

annotated_encoder_decoder

The Annotated Encoder Decoder with Attention

e-SNLI

lstms.pth

PyTorch implementations of LSTM Variants (Dropout + Layer Norm)

Better_LSTM_PyTorch

An LSTM in PyTorch with best practices (weight dropout, forget bias, etc.) built-in. Fully compatible with PyTorch LSTM.

eraserbenchmark

A benchmark for understanding and evaluating rationales: http://www.eraserbenchmark.com/

sparselandtools

:sparkles: A Python package for sparse representations and dictionary learning, including matching pursuit, K-SVD and applications.

latent-treelstm

Cooperative Learning of Disjoint Syntax and Semantics

VirtualTeaching

DIY setup for virtual teaching on ubuntu

FRESH

Textual-Entailment-New-Protocols

This data release is meant to accompany and document the paper: https://arxiv.org/abs/2004.11997 Collecting Entailment Data for Pretraining: New Protocols and Negative Results by Samuel R. Bowman, Jennimaria Palomaki, Livio Baldini Soares, and Emily Pitler