Merge branch 'main' of https://huggingface.co/pkshatech/simcse-ja-bert-base-clcmlp
Browse files- tokenizer_config.json +3 -5
tokenizer_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
"do_lower_case": false,
|
4 |
"do_subword_tokenize": true,
|
5 |
"do_word_tokenize": true,
|
@@ -15,8 +14,7 @@
|
|
15 |
"sep_token": "[SEP]",
|
16 |
"special_tokens_map_file": null,
|
17 |
"subword_tokenizer_type": "wordpiece",
|
18 |
-
"
|
19 |
-
|
20 |
-
|
21 |
-
"word_tokenizer_type": "mecab"
|
22 |
}
|
|
|
1 |
{
|
|
|
2 |
"do_lower_case": false,
|
3 |
"do_subword_tokenize": true,
|
4 |
"do_word_tokenize": true,
|
|
|
14 |
"sep_token": "[SEP]",
|
15 |
"special_tokens_map_file": null,
|
16 |
"subword_tokenizer_type": "wordpiece",
|
17 |
+
"mecab_kwargs": {
|
18 |
+
"mecab_dic": "unidic_lite"
|
19 |
+
}
|
|
|
20 |
}
|