CoreML version of sentence transformer for sentence embeddings, text matching or semantic search.
This repository contains:
- For Tokenizer:
- pretrained Google BERT and Hugging Face DistilBERT models fine-tuned for Question answering on the SQuAD dataset.
- Swift implementations of the BERT tokenizer (
BasicTokenizer
andWordpieceTokenizer
) and SQuAD dataset parsing utilities.
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-lfs
on the installation page