From c615df74224ec5d416278c2d4dc34f239a77aad9 Mon Sep 17 00:00:00 2001 From: joangines Date: Fri, 11 Dec 2020 23:40:14 +0900 Subject: [PATCH] Create README.md (#8751) * Create README.md * Update model_cards/Cinnamon/electra-small-japanese-generator/README.md Co-authored-by: Julien Chaumond --- .../electra-small-japanese-generator/README.md | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 model_cards/Cinnamon/electra-small-japanese-generator/README.md diff --git a/model_cards/Cinnamon/electra-small-japanese-generator/README.md b/model_cards/Cinnamon/electra-small-japanese-generator/README.md new file mode 100644 index 0000000000..0e014328e7 --- /dev/null +++ b/model_cards/Cinnamon/electra-small-japanese-generator/README.md @@ -0,0 +1,18 @@ +--- +language: ja +--- +## Japanese ELECTRA-small + +We provide a Japanese **ELECTRA-Small** model, as described in [ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators](https://openreview.net/pdf?id=r1xMH1BtvB). + +Our pretraining process employs subword units derived from the [Japanese Wikipedia](https://dumps.wikimedia.org/jawiki/latest), using the [Byte-Pair Encoding](https://www.aclweb.org/anthology/P16-1162.pdf) method and building on an initial tokenization with [mecab-ipadic-NEologd](https://github.com/neologd/mecab-ipadic-neologd). For optimal performance, please take care to set your MeCab dictionary appropriately. + +``` +# ELECTRA-small generator usage + +from transformers import BertJapaneseTokenizer, ElectraForMaskedLM + +tokenizer = BertJapaneseTokenizer.from_pretrained('Cinnamon/electra-small-japanese-generator', mecab_kwargs={"mecab_option": "-d /usr/lib/x86_64-linux-gnu/mecab/dic/mecab-ipadic-neologd"}) + +model = ElectraForMaskedLM.from_pretrained('Cinnamon/electra-small-japanese-generator') +```