Skip to content

Latest commit

 

History

History
8 lines (8 loc) · 432 Bytes

File metadata and controls

8 lines (8 loc) · 432 Bytes

Code information

  • Src
    • bleu.py is used to generate the bleu scores of a translation.
    • data.py contains the code related to data processing, tokenization, dataset, collate_fn.
    • multihead_attention.py contains multihead attention code.
    • transformer.py contain the implementation of the transformer model.
    • train.py is used to train the transformer.
  • environment.yaml contains the conda environment used.