Skip to content
Swift Core ML 3 implementation of BERT for Question answering
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
CoreMLBert.xcodeproj Demo UI is awesome Jun 28, 2019
CoreMLBert `en-US` voice is actually better Jul 1, 2019
CoreMLBertTests Hook prediction Jun 28, 2019
Resources Wordpiece to string Jun 28, 2019
Sources Hook prediction Jun 28, 2019
media Add demo gif to readme Jun 28, 2019
.gitattributes git lfs add mlmodel Jun 27, 2019
.gitignore Initial Commit Jun 27, 2019
README.md Add demo gif to readme Jun 28, 2019

README.md

Swift Core ML implementation of BERT

This repository contains:

  • a pretrained Google BERT model fine-tuned for Question answering on the SQuAD dataset.
  • Swift implementations of the BERT tokenizer (BasicTokenizer and WordpieceTokenizer) and SQuAD dataset parsing utilities.
  • A demo question answering app.

The pretrained Core ML model was packaged by Apple and is linked from the main ML models page. It was demoed at WWDC 2019 as part of the Core ML 3 launch.

core ml 3

🦄 Demo Time 🔥

demo

Apple demo at WWDC 2019

wwdc demo

full video here

BERT Architecture (wwdc slide)

bert

Notes

We use git-lfs to store large model files and it is required to obtain some of the files the app needs to run. See how to install git-lfson the installation page

You can’t perform that action at this time.