by jadore801120

A PyTorch implementation of the Transformer model in "Attention is All You Need".

4.3K Stars 1.1K Forks Last release: Not found MIT License 191 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:

Attention is all you need: A Pytorch Implementation

This is a PyTorch implementation of the Transformer model in "Attention is All You Need" (Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin, arxiv, 2017).

A novel sequence to sequence framework utilizes the self-attention mechanism, instead of Convolution operation or Recurrent structure, and achieve the state-of-the-art performance on WMT 2014 English-to-German translation task. (2017/06/12)

The official Tensorflow Implementation can be found in: tensorflow/tensor2tensor.

To learn more about self-attention mechanism, you could read "A Structured Self-attentive Sentence Embedding".

The project support training and translation with trained model now.

Note that this project is still a work in progress.

BPE related parts are not yet fully tested.

If there is any suggestion or error, feel free to fire an issue to let me know. :)


  • python 3.4+
  • pytorch 1.3.1
  • torchtext 0.4.0
  • spacy 2.2.2+
  • tqdm
  • dill
  • numpy


WMT'16 Multimodal Translation: de-en

An example of training for the WMT'16 Multimodal Translation task (

0) Download the spacy language model.

# conda install -c conda-forge spacy 
python -m spacy download en
python -m spacy download de

1) Preprocess the data with torchtext and spacy.

python -lang_src de -lang_trg en -share_vocab -save_data m30k_deen_shr.pkl

2) Train the model

python -data_pkl m30k_deen_shr.pkl -log m30k_deen_shr -embs_share_weight -proj_share_weight -label_smoothing -save_model trained -b 256 -warmup 128000 -epoch 400

3) Test the model

python -data_pkl m30k_deen_shr.pkl -model trained.chkpt -output prediction.txt

[(WIP)] WMT'17 Multimodal Translation: de-en w/ BPE

1) Download and preprocess the data with bpe:

Since the interfaces is not unified, you need to switch the main function call from

python -raw_dir /tmp/raw_deen -data_dir ./bpe_deen -save_data bpe_vocab.pkl -codes codes.txt -prefix deen

2) Train the model

python -data_pkl ./bpe_deen/bpe_vocab.pkl -train_path ./bpe_deen/deen-train -val_path ./bpe_deen/deen-val -log deen_bpe -embs_share_weight -proj_share_weight -label_smoothing -save_model trained -b 256 -warmup 128000 -epoch 400

3) Test the model (not ready)

  • TODO:
    • Load vocabulary.

    - Perform decoding after the translation.



  • Parameter settings:

    • default parameter and optimizer settings
    • label smoothing
    • target embedding / pre-softmax linear layer weight sharing.
  • Elapse per epoch (on NVIDIA Titan X):

    • Training set: 0.888 minutes
    • Validation set: 0.011 minutes


- coming soon.


  • Evaluation on the generated text.

- Attention weight plot.


  • The byte pair encoding parts are borrowed from subword-nmt.
  • The project structure, some scripts and the dataset preprocessing steps are heavily borrowed from OpenNMT/OpenNMT-py.
  • Thanks for the suggestions from @srush, @iamalbert, @Zessay, @JulesGM and @ZiJianZhao.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.