From 30931391d343019f266e556bdaa897cf2fd19b2d Mon Sep 17 00:00:00 2001 From: system Date: Sun, 7 Jun 2020 12:26:07 +0000 Subject: [PATCH] Update tokenizer_config.json --- tokenizer_config.json | 5 +++++ 1 file changed, 5 insertions(+) create mode 100644 tokenizer_config.json diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..533b68c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,5 @@ +{ + "do_lower_case": false, + "word_tokenizer_type": "mecab", + "subword_tokenizer_type": "wordpiece" +}