update tokenizer_config.json

tokenizer_config.json

@@ -1 +1,19 @@
-{"do_lower_case": false, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "sudachipy", "subword_tokenizer_type": "pos_substitution", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "word_form_type": "surface", "sudachipy_kwargs": null, "use_fast": false, "tokenizer_class": "sudachitra.tokenization_electra_sudachipy.ElectraSudachipyTokenizer"}
+{
+ "use_fast": false,
+ "tokenizer_class": "sudachitra.tokenization_electra_sudachipy.ElectraSudachipyTokenizer",
+ "do_lower_case": false,
+ "do_word_tokenize": true,
+ "do_subword_tokenize": true,
+ "word_tokenizer_type": "sudachipy",
+ "subword_tokenizer_type": "wordpiece",
+ "word_form_type": "dictionary_and_surface",
+ "sudachipy_kwargs": {
+  "split_mode": "A",
+  "dict_type": "core"
+ },
+ "unk_token": "[UNK]",
+ "sep_token": "[SEP]",
+ "pad_token": "[PAD]",
+ "cls_token": "[CLS]",
+ "mask_token": "[MASK]"
+}