edwardjhu

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

hierarchical-language-model

improved_wasserstein

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

parabank-demo

TP4

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

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

mup

maximal update parametrization (µP)

edwardjhu/TP4

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

edwardjhu/improved_wasserstein

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

edwardjhu/hierarchical-language-model

edwardjhu/parabank-demo

edwardjhu/apex

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

edwardjhu/DeBERTa

The implementation of DeBERTa

edwardjhu/edwardjhu.github.io

edwardjhu/facenet-pytorch

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

edwardjhu/fairseq

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

edwardjhu/Megatron-LM

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

edwardjhu/oldsru

edwardjhu/robustness

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

edwardjhu/sockeye

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

edwardjhu/block-recurrent-transformer

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

edwardjhu/chat-edu

edwardjhu/indigo

:ramen: Minimalist Jekyll Template

edwardjhu/MoE

edwardjhu/pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

edwardjhu/second-brain