Commit
•
c547c15
1
Parent(s):
4c3dbc7
Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer_config.json +21 -0
- vocab.txt +0 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"do_subword_tokenize": true,
|
| 6 |
+
"do_word_tokenize": true,
|
| 7 |
+
"jumanpp_kwargs": null,
|
| 8 |
+
"mask_token": "[MASK]",
|
| 9 |
+
"mecab_kwargs": {
|
| 10 |
+
"mecab_dic": "unidic_lite"
|
| 11 |
+
},
|
| 12 |
+
"model_max_length": 512,
|
| 13 |
+
"never_split": null,
|
| 14 |
+
"pad_token": "[PAD]",
|
| 15 |
+
"sep_token": "[SEP]",
|
| 16 |
+
"subword_tokenizer_type": "wordpiece",
|
| 17 |
+
"sudachi_kwargs": null,
|
| 18 |
+
"tokenizer_class": "BertJapaneseTokenizer",
|
| 19 |
+
"unk_token": "[UNK]",
|
| 20 |
+
"word_tokenizer_type": "mecab"
|
| 21 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|