Julia Implementation of Transformer models
Author chengchingwen
191 Stars
Updated Last
1 Year Ago
Started In
December 2018

Build status codecov

Julia implementation of transformer-based models, with Flux.jl.


In the Julia REPL:

]add Transformers

For using GPU, install & build:

]add CUDA


julia> using CUDA

julia> using Transformers

#run the model below


Using pretrained Bert with Transformers.jl.

using Transformers
using Transformers.Basic
using Transformers.Pretrain


bert_model, wordpiece, tokenizer = pretrain"bert-uncased_L-12_H-768_A-12"
vocab = Vocabulary(wordpiece)

text1 = "Peter Piper picked a peck of pickled peppers" |> tokenizer |> wordpiece
text2 = "Fuzzy Wuzzy was a bear" |> tokenizer |> wordpiece

text = ["[CLS]"; text1; "[SEP]"; text2; "[SEP]"]
@assert text == [
    "[CLS]", "peter", "piper", "picked", "a", "peck", "of", "pick", "##led", "peppers", "[SEP]", 
    "fuzzy", "wu", "##zzy",  "was", "a", "bear", "[SEP]"

token_indices = vocab(text)
segment_indices = [fill(1, length(text1)+2); fill(2, length(text2)+1)]

sample = (tok = token_indices, segment = segment_indices)

bert_embedding = sample |> bert_model.embed
feature_tensors = bert_embedding |> bert_model.transformers

See example folder for the complete example.


We have some support for the models from huggingface/transformers.

using Transformers.HuggingFace

# loading a model from huggingface model hub
julia> model = hgf"bert-base-cased:forquestionanswering";
┌ Warning: Transformers.HuggingFace.HGFBertForQuestionAnswering doesn't have field cls.
└ @ Transformers.HuggingFace ~/peter/repo/gsoc2020/src/huggingface/models/models.jl:46
┌ Warning: Some fields of Transformers.HuggingFace.HGFBertForQuestionAnswering aren't initialized with loaded state: qa_outputs
└ @ Transformers.HuggingFace ~/peter/repo/gsoc2020/src/huggingface/models/models.jl:52

Current we only support a few model and the tokenizer part is not finished yet.

For more information

If you want to know more about this package, see the document and the series of blog posts I wrote for JSoC and GSoC. You can also tag me (@chengchingwen) on Julia's slack or discourse if you have any questions, or just create a new Issue on GitHub.


What we have before v0.2

  • Transformer and TransformerDecoder support for both 2d & 3d data.
  • PositionEmbedding implementation.
  • Positionwise for handling 2d & 3d input.
  • docstring for most of the functions.
  • runable examples (see example folder)
  • Transformers.HuggingFace for handling pretrains from huggingface/transformers

What we will have in v0.2.0

  • Complete tokenizer APIs
  • tutorials
  • benchmarks
  • more examples