DeLighT: Very Deep and Light-Weight Transformers

Related tags

Deep Learningdelight
Overview

DeLighT: Very Deep and Light-weight Transformers

This repository contains the source code of our work on building efficient sequence models: DeFINE (ICLR'20) and DeLighT (preprint).

Table of contents

  1. Overview
  2. Requirements and installation
  3. Training, evaluation, and results
  4. Multiplication-addition operations
  5. Citation
  6. Acknowledgement
  7. Issues

Overview

In this repository, we share the source code of our paper DeLight, that delivers similar or better performance than transformer-based models with significantly fewer parameters. DeLighT more efficiently allocates parameters both (1) within each Transformer block using DExTra, a deep and light-weight transformation and (2) across blocks using block-wise scaling, that allows for shallower and narrower DeLighT blocks near the input and wider and deeper DeLighT blocks near the output. Overall, DeLighT networks are 2.5 to 4 times deeper than standard transformer models and yet have fewer parameters and operations. For details, see our papers: DeFINE and and DeLighT.

DeLighT unit

Requirements and Installation

  • PyTorch version >= 1.4.0
  • Python version >= 3.6
  • For training new models, you'll also need an NVIDIA GPU and NCCL
  • To use DeLighT, you need to install fairseq and develop locally:
git clone https://github.com/sacmehta/delight
cd delight
pip install --editable ./
  • For faster training install NVIDIA's apex library:
git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" \
  --global-option="--deprecated_fused_adam" --global-option="--xentropy" \
  --global-option="--fast_multihead_attn" ./

Training, Evaluation, and Results

For training, evaluation, and results, see below links. To ease reproduction of our results, we also provide links to training logs.

Neural machine translation

Language Modeling

Multiplication-Addition Operations

We have added module profiling for both Transformer and DeLight networks. This can be enabled using --print-stats argument. A model summary will be printed (by default for 20 tokens), similar to below screenshot. To use larger sequence lengths for source and target for profiling statistics, you can use --src-len-ps and --tgt-len-ps flags.

Model statistics

Citation

If you find our work useful, please consider citing following works:

@misc{mehta2020delight,
    title={DeLighT: Very Deep and Light-weight Transformer},
    author={Sachin Mehta and Marjan Ghazvininejad and Srinivasan Iyer and Luke Zettlemoyer and Hannaneh Hajishirzi},
    year={2020},
    eprint={2008.00623},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}
@inproceedings{mehta2019define,
  title={DeFINE: Deep Factorized Input Token Embeddings for Neural Sequence Modeling},
  author={Mehta, Sachin and Koncel-Kedziorski, Rik and Rastegari, Mohammad and Hajishirzi, Hannaneh},
  booktitle={International Conference on Learning Representations},
  year={2019}
}

Acknowledgements

We would like to thank Fairseq team for building easy-to-use sequence library.

Issues

Thanks for your interest in our work. For any issues, please raise a request.

Owner
Sachin Mehta
Ph.D. Student at University of Washington
Sachin Mehta
PyTorch implementation of the paper Ultra Fast Structure-aware Deep Lane Detection

PyTorch implementation of the paper Ultra Fast Structure-aware Deep Lane Detection

1.4k Jan 06, 2023
Python package to add text to images, textures and different backgrounds

nider Python package for text images generation and watermarking Free software: MIT license Documentation: https://nider.readthedocs.io. nider is an a

Vladyslav Ovchynnykov 131 Dec 30, 2022
Code to reproduce the results for Statistically Robust Neural Network Classification, published in UAI 2021

Code to reproduce the results for Statistically Robust Neural Network Classification, published in UAI 2021

1 Jun 02, 2022
Distributed Asynchronous Hyperparameter Optimization better than HyperOpt.

UltraOpt : Distributed Asynchronous Hyperparameter Optimization better than HyperOpt. UltraOpt is a simple and efficient library to minimize expensive

98 Aug 16, 2022
Implementation and replication of ProGen, Language Modeling for Protein Generation, in Jax

ProGen - (wip) Implementation and replication of ProGen, Language Modeling for Protein Generation, in Pytorch and Jax (the weights will be made easily

Phil Wang 71 Dec 01, 2022
This repo in the implementation of EMNLP'21 paper "SPARQLing Database Queries from Intermediate Question Decompositions" by Irina Saparina, Anton Osokin

SPARQLing Database Queries from Intermediate Question Decompositions This repo is the implementation of the following paper: SPARQLing Database Querie

Yandex Research 20 Dec 19, 2022
On-device speech-to-intent engine powered by deep learning

Rhino Made in Vancouver, Canada by Picovoice Rhino is Picovoice's Speech-to-Intent engine. It directly infers intent from spoken commands within a giv

Picovoice 510 Dec 30, 2022
BankNote-Net: Open dataset and encoder model for assistive currency recognition

BankNote-Net: Open Dataset for Assistive Currency Recognition Millions of people around the world have low or no vision. Assistive software applicatio

Microsoft 13 Oct 28, 2022
Code for the bachelors-thesis flaky fault localization

Flaky_Fault_Localization Scripts for the Bachelors-Thesis: "Flaky Fault Localization" by Christian Kasberger. The thesis examines the usefulness of sp

Christian Kasberger 1 Oct 26, 2021
A Convolutional Transformer for Keyword Spotting

☢️ Audiomer ☢️ Audiomer: A Convolutional Transformer for Keyword Spotting [ arXiv ] [ Previous SOTA ] [ Model Architecture ] Results on SpeechCommands

49 Jan 27, 2022
Implementation of ToeplitzLDA for spatiotemporal stationary time series data.

Code for the ToeplitzLDA classifier proposed in here. The classifier conforms sklearn and can be used as a drop-in replacement for other LDA classifiers. For in-depth usage refer to the learning from

Jan Sosulski 5 Nov 07, 2022
SCU OlympicsRunning Baseline

Competition 1v1 running Environment check details in Jidi Competition RLChina2021智能体竞赛 做出的修改: 奖励重塑:修改了环境,重新设置了奖励的分配,使得奖励组成不只有零和博弈,还有探索环境的奖励。 算法微调:修改了官

ZiSeoi Wong 2 Nov 23, 2021
Code for AutoNL on ImageNet (CVPR2020)

Neural Architecture Search for Lightweight Non-Local Networks This repository contains the code for CVPR 2020 paper Neural Architecture Search for Lig

Yingwei Li 104 Aug 31, 2022
TensorFlow implementation of the paper "Hierarchical Attention Networks for Document Classification"

Hierarchical Attention Networks for Document Classification This is an implementation of the paper Hierarchical Attention Networks for Document Classi

Quoc-Tuan Truong 83 Dec 05, 2022
Official Code Release for "CLIP-Adapter: Better Vision-Language Models with Feature Adapters"

Official Code Release for "CLIP-Adapter: Better Vision-Language Models with Feature Adapters" Pipeline of CLIP-Adapter CLIP-Adapter is a drop-in modul

peng gao 157 Dec 26, 2022
A paper using optimal transport to solve the graph matching problem.

GOAT A paper using optimal transport to solve the graph matching problem. https://arxiv.org/abs/2111.05366 Repo structure .github: Files specifying ho

neurodata 8 Jan 04, 2023
This repository contains the segmentation user interface from the OpenSurfaces project, extracted as a lightweight tool

OpenSurfaces Segmentation UI This repository contains the segmentation user interface from the OpenSurfaces project, extracted as a lightweight tool.

Sean Bell 66 Jul 11, 2022
This is a file about Unet implemented in Pytorch

Unet this is an implemetion of Unet in Pytorch and it's architecture is as follows which is the same with paper of Unet component of Unet Convolution

Dragon 1 Dec 03, 2021
(NeurIPS '21 Spotlight) IQ-Learn: Inverse Q-Learning for Imitation

Inverse Q-Learning (IQ-Learn) Official code base for IQ-Learn: Inverse soft-Q Learning for Imitation, NeurIPS '21 Spotlight IQ-Learn is an easy-to-use

Divyansh Garg 102 Dec 20, 2022
PyTorch implementation of the REMIND method from our ECCV-2020 paper "REMIND Your Neural Network to Prevent Catastrophic Forgetting"

REMIND Your Neural Network to Prevent Catastrophic Forgetting This is a PyTorch implementation of the REMIND algorithm from our ECCV-2020 paper. An ar

Tyler Hayes 72 Nov 27, 2022