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
Black box hyperparameter optimization made easy.

BBopt BBopt aims to provide the easiest hyperparameter optimization you'll ever do. Think of BBopt like Keras (back when Theano was still a thing) for

Evan Hubinger 70 Nov 03, 2022
Subgraph Based Learning of Contextual Embedding

SLiCE Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks Dataset details: We use four public benchmark da

Pacific Northwest National Laboratory 27 Dec 01, 2022
Mesh Graphormer is a new transformer-based method for human pose and mesh reconsruction from an input image

MeshGraphormer ✨ ✨ This is our research code of Mesh Graphormer. Mesh Graphormer is a new transformer-based method for human pose and mesh reconsructi

Microsoft 251 Jan 08, 2023
A short and easy PyTorch implementation of E(n) Equivariant Graph Neural Networks

Simple implementation of Equivariant GNN A short implementation of E(n) Equivariant Graph Neural Networks for HOMO energy prediction. Just 50 lines of

Arsenii Senya Ashukha 97 Dec 23, 2022
Implementation of the paper "Language-agnostic representation learning of source code from structure and context".

Code Transformer This is an official PyTorch implementation of the CodeTransformer model proposed in: D. Zügner, T. Kirschstein, M. Catasta, J. Leskov

Daniel Zügner 131 Dec 13, 2022
The King is Naked: on the Notion of Robustness for Natural Language Processing

the-king-is-naked: on the notion of robustness for natural language processing AAAI2022 DISCLAIMER:This repo will be updated soon with instructions on

Iperboreo_ 1 Nov 24, 2022
ByteTrack with ReID module following the paradigm of FairMOT, tracking strategy is borrowed from FairMOT/JDE.

ByteTrack_ReID ByteTrack is the SOTA tracker in MOT benchmarks with strong detector YOLOX and a simple association strategy only based on motion infor

Han GuangXin 46 Dec 29, 2022
Calibrated Hyperspectral Image Reconstruction via Graph-based Self-Tuning Network.

mask-uncertainty-in-HSI This repository contains the testing code and pre-trained models for the paper Calibrated Hyperspectral Image Reconstruction v

JIAMIAN WANG 9 Dec 29, 2022
An auto discord account and token generator. Automatically verifies the phone number. Works without proxy. Bypasses captcha.

JOIN DISCORD SERVER https://discord.gg/uAc3agBY FREE HCAPTCHA SOLVING API Discord-Token-Gen An auto discord token generator. Auto verifies phone numbe

3kp 271 Jan 01, 2023
Open-AI's DALL-E for large scale training in mesh-tensorflow.

DALL-E in Mesh-Tensorflow [WIP] Open-AI's DALL-E in Mesh-Tensorflow. If this is similarly efficient to GPT-Neo, this repo should be able to train mode

EleutherAI 432 Dec 16, 2022
CoMoGAN: continuous model-guided image-to-image translation. CVPR 2021 oral.

CoMoGAN: Continuous Model-guided Image-to-Image Translation Official repository. Paper CoMoGAN: continuous model-guided image-to-image translation [ar

166 Dec 31, 2022
A Self-Supervised Contrastive Learning Framework for Aspect Detection

AspDecSSCL A Self-Supervised Contrastive Learning Framework for Aspect Detection This repository is a pytorch implementation for the following AAAI'21

Tian Shi 30 Dec 28, 2022
codes for paper Combining Dynamic Local Context Focus and Dependency Cluster Attention for Aspect-level sentiment classification

DLCF-DCA codes for paper Combining Dynamic Local Context Focus and Dependency Cluster Attention for Aspect-level sentiment classification. submitted t

15 Aug 30, 2022
The Official PyTorch Implementation of "LSGM: Score-based Generative Modeling in Latent Space" (NeurIPS 2021)

The Official PyTorch Implementation of "LSGM: Score-based Generative Modeling in Latent Space" (NeurIPS 2021) Arash Vahdat*   ·   Karsten Kreis*   ·  

NVIDIA Research Projects 238 Jan 02, 2023
Pytorch implementation of MaskFlownet

MaskFlownet-Pytorch Unofficial PyTorch implementation of MaskFlownet (https://github.com/microsoft/MaskFlownet). Tested with: PyTorch 1.5.0 CUDA 10.1

Daniele Cattaneo 84 Nov 02, 2022
Tutorial to set up TensorFlow Object Detection API on the Raspberry Pi

A tutorial showing how to set up TensorFlow's Object Detection API on the Raspberry Pi

Evan 1.1k Dec 26, 2022
Code associated with the paper "Deep Optics for Single-shot High-dynamic-range Imaging"

Deep Optics for Single-shot High-dynamic-range Imaging Code associated with the paper "Deep Optics for Single-shot High-dynamic-range Imaging" CVPR, 2

Stanford Computational Imaging Lab 40 Dec 12, 2022
Graph Analysis From Scratch

Graph Analysis From Scratch Goal In this notebook we wanted to implement some functionalities to analyze a weighted graph only by using algorithms imp

Arturo Ghinassi 0 Sep 17, 2022
Hidden-Fold Networks (HFN): Random Recurrent Residuals Using Sparse Supermasks

Hidden-Fold Networks (HFN): Random Recurrent Residuals Using Sparse Supermasks by Ángel López García-Arias, Masanori Hashimoto, Masato Motomura, and J

Ángel López García-Arias 4 May 19, 2022
List of papers, code and experiments using deep learning for time series forecasting

Deep Learning Time Series Forecasting List of state of the art papers focus on deep learning and resources, code and experiments using deep learning f

Alexander Robles 2k Jan 06, 2023