Upload 4 files
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +2 -2
- vocab.txt +0 -0
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -3,11 +3,11 @@
|
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_lower_case": false,
|
5 |
"mask_token": "[MASK]",
|
6 |
-
"model_max_length":
|
7 |
"pad_token": "[PAD]",
|
8 |
"sep_token": "[SEP]",
|
9 |
"strip_accents": null,
|
10 |
-
"tokenize_chinese_chars":
|
11 |
"tokenizer_class": "BertTokenizer",
|
12 |
"unk_token": "[UNK]"
|
13 |
}
|
|
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_lower_case": false,
|
5 |
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 33000,
|
7 |
"pad_token": "[PAD]",
|
8 |
"sep_token": "[SEP]",
|
9 |
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
"tokenizer_class": "BertTokenizer",
|
12 |
"unk_token": "[UNK]"
|
13 |
}
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|