Commit
•
6b4704c
1
Parent(s):
2b4c5ad
revise tokenizer settings
Browse files- tokenizer_config.json +4 -1
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,10 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"do_lower_case": false,
|
|
|
|
|
|
|
| 3 |
"word_tokenizer_type": "sudachipy",
|
| 4 |
-
"word_form_type": "
|
| 5 |
"subword_tokenizer_type": "wordpiece",
|
| 6 |
"model_max_length": 512,
|
| 7 |
"sudachipy_kwargs": {"split_mode":"A","dict_type":"core"}
|
|
|
|
| 1 |
{
|
| 2 |
+
"tokenizer_class": "sudachitra.tokenization_electra_sudachipy.ElectraSudachipyTokenizer",
|
| 3 |
"do_lower_case": false,
|
| 4 |
+
"do_word_tokenize": true,
|
| 5 |
+
"do_subword_tokenize": true,
|
| 6 |
"word_tokenizer_type": "sudachipy",
|
| 7 |
+
"word_form_type": "dictionary_and_surface",
|
| 8 |
"subword_tokenizer_type": "wordpiece",
|
| 9 |
"model_max_length": 512,
|
| 10 |
"sudachipy_kwargs": {"split_mode":"A","dict_type":"core"}
|