Transformer on a Diet

Reference: C Wang, Z Ye, A Zhang, Z Zhang, A Smola. "Transformer on a Diet". arXiv preprint arXiv (2020).

Installation

pip install --pre --upgrade mxnet
pip install gluonnlp

Results

The results and the command line to reproduce the results on PTB dataset are as follows.

[1] Full (Val PPL 109.19 Test PPL 103.72)

$ cd scripts/language_model/
$ python transformer_language_model.py --model full --data ptb --emsize 320 --nhid 2000 --nlayers 3 --lr 10 --epochs 500 --batch_size 20 --bptt 70 --dropout 0.4 --dropout_h 0.25 --dropout_i 0 --dropout_e 0 --weight_drop 0 --tied --alpha 0 --beta 0 --lr_update_interval 100 --lr_update_factor 1 --num_heads 16 --scaled --units 320 --use_residual --max_src_length 1000 --warmup_steps 0 --first_window_size 1 --kernel_size 3 --d_base 2

[2] Dilated (Val PPL 115.67 Test PPL 110.92)

$ cd scripts/language_model/
$ python transformer_language_model.py --model dilated --data ptb --emsize 320 --nhid 2000 --nlayers 3 --lr 10 --epochs 500 --batch_size 20 --bptt 70 --dropout 0.4 --dropout_h 0.25 --dropout_i 0 --dropout_e 0 --weight_drop 0 --tied --alpha 0 --beta 0 --lr_update_interval 100 --lr_update_factor 1 --num_heads 16 --scaled --units 320 --use_residual --max_src_length 1000 --warmup_steps 0 --first_window_size 1 --kernel_size 3 --d_base 2

[3] Dilated-Memory (Val PPL 115.35 Test PPL 110.98)

$ cd scripts/language_model/
$ python transformer_language_model.py --model dilated_mem --data ptb --emsize 320 --nhid 2000 --nlayers 3 --lr 10 --epochs 500 --batch_size 20 --bptt 70 --dropout 0.4 --dropout_h 0.25 --dropout_i 0 --dropout_e 0 --weight_drop 0 --tied --alpha 0 --beta 0 --lr_update_interval 100 --lr_update_factor 1 --num_heads 16 --scaled --units 320 --use_residual --max_src_length 1000 --warmup_steps 0 --first_window_size 1 --kernel_size 3 --d_base 2

[4] Cascade (Val PPL 109.16 Test PPL 105.27)

$ cd scripts/language_model/
$ python transformer_language_model.py --model cascade --data ptb --emsize 320 --nhid 2000 --nlayers 3 --lr 10 --epochs 500 --batch_size 20 --bptt 70 --dropout 0.4 --dropout_h 0.25 --dropout_i 0 --dropout_e 0 --weight_drop 0 --tied --alpha 0 --beta 0 --lr_update_interval 100 --lr_update_factor 1 --num_heads 16 --scaled --units 320 --use_residual --max_src_length 1000 --warmup_steps 0 --first_window_size 4 --window_size_multiplier 2 --kernel_size 3 --d_base 2

Note that the command to reproduce the results on wikitext-2 would be updated soon.

Reference Paper

The bibtext entry of the reference paper is:

@article{transformerdiet2020,
   title={Transformer on a Diet},
   author={Chenguang Wang and Zihao Ye and Aston Zhang and Zheng Zhang and Alexander J. Smola},
   journal={ArXiv},
   year={2020},
   volume={abs/2002.06170}
}

Code repo for "Transformer on a Diet" paper

Related tags

Overview

Transformer on a Diet

Installation

Results

Reference Paper

Owner

cgraywang

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

Using LSTM write Tang poetry

Irrigation controller for Home Assistant

Gesture-Volume-Control - This Python program can adjust the system's volume by using hand gestures

A simple approach to emable dense segmentation with ViT.

This is the face keypoint train code of project face-detection-project

Referring Video Object Segmentation

VOGUE: Try-On by StyleGAN Interpolation Optimization

A parallel framework for population-based multi-agent reinforcement learning.

[NeurIPS 2021] “Improving Contrastive Learning on Imbalanced Data via Open-World Sampling”,

EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation (CVPR'21)

3rd Place Solution of the Traffic4Cast Core Challenge @ NeurIPS 2021

Can we learn gradients by Hamiltonian Neural Networks?

Fashion Recommender System With Python

RoBERTa Marathi Language model trained from scratch during huggingface 🤗 x flax community week

The open-source and free to use Python package miseval was developed to establish a standardized medical image segmentation evaluation procedure

ilpyt: imitation learning library with modular, baseline implementations in Pytorch

Implementation of our recent paper, WOOD: Wasserstein-based Out-of-Distribution Detection.

Evaluating AlexNet features at various depths

Official codebase for running the small, filtered-data GLIDE model from GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.