edwardjhu

TP4

Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)

improved_wasserstein

Code for our ICLR Trustworthy ML 2020 workshop paper "Improved Image Wasserstein Attacks and Defenses"

parabank-demo

apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

DeBERTa

The implementation of DeBERTa

edwardjhu.github.io

facenet-pytorch

Pretrained Pytorch face detection (MTCNN) and recognition (InceptionResnet) models

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

hierarchical-language-model

Megatron-LM

Ongoing research training transformer language models at scale, including: BERT & GPT-2

oldsru

robustness

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

sockeye

Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet

block-recurrent-transformer

Pytorch implementation of "Block Recurrent Transformers" (Hutchins & Schlag et al., 2022)

indigo

:ramen: Minimalist Jekyll Template

MoE

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration