CodeBERTaJS

CodeBERTaJS is a RoBERTa-like model trained on the CodeSearchNet dataset from GitHub for javaScript by Manuel Romero

The tokenizer is a Byte-level BPE tokenizer trained on the corpus using Hugging Face tokenizers.

Because it is trained on a corpus of code (vs. natural language), it encodes the corpus efficiently (the sequences are between 33% to 50% shorter, compared to the same corpus tokenized by gpt2/roberta).

The (small) model is a 6-layer, 84M parameters, RoBERTa-like Transformer model – that’s the same number of layers & heads as DistilBERT – initialized from the default initialization settings and trained from scratch on the full javascript corpus (120M after preproccessing) for 2 epochs.

Quick start: masked language modeling prediction

JS_CODE = """
async function createUser(req, <mask>) {
  if (!validUser(req.body.user)) {
\t  return res.status(400);
  }
  user = userService.createUser(req.body.user);
  return res.json(user);
}
""".lstrip()

Does the model know how to complete simple JS/express like code?

from transformers import pipeline

fill_mask = pipeline(
    "fill-mask",
    model="mrm8488/codeBERTaJS",
    tokenizer="mrm8488/codeBERTaJS"
)

fill_mask(JS_CODE)

## Top 5 predictions:
#
'res' # prob  0.069489665329
'next'
'req'
'user'
',req'

Yes! That was easy 🎉 Let's try with another example

JS_CODE_= """
function getKeys(obj) {
  keys = [];
  for (var [key, value] of Object.entries(obj)) {
     keys.push(<mask>);
  }
  return keys
}
""".lstrip()

Results:

'obj', 'key', ' value', 'keys', 'i'

Not so bad! Right token was predicted as second option! 🎉

This work is heavely inspired on codeBERTa by huggingface team

CodeSearchNet citation

@article{husain_codesearchnet_2019,
\ttitle = {{CodeSearchNet} {Challenge}: {Evaluating} the {State} of {Semantic} {Code} {Search}},
\tshorttitle = {{CodeSearchNet} {Challenge}},
\turl = {http://arxiv.org/abs/1909.09436},
\turldate = {2020-03-12},
\tjournal = {arXiv:1909.09436 [cs, stat]},
\tauthor = {Husain, Hamel and Wu, Ho-Hsiang and Gazit, Tiferet and Allamanis, Miltiadis and Brockschmidt, Marc},
\tmonth = sep,
\tyear = {2019},
\tnote = {arXiv: 1909.09436},
}

Created by Manuel Romero/@mrm8488

Made with ♥ in Spain