scherrmann
commited on
Commit
·
d5826ec
1
Parent(s):
4c8d9e8
Upload 4 files
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +1 -4
- vocab.txt +0 -0
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,15 +1,12 @@
|
|
1 |
{
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
-
"do_basic_tokenize": true,
|
5 |
"do_lower_case": false,
|
6 |
"mask_token": "[MASK]",
|
7 |
-
"max_len": 512,
|
8 |
"model_max_length": 512,
|
9 |
-
"never_split": null,
|
10 |
"pad_token": "[PAD]",
|
11 |
"sep_token": "[SEP]",
|
12 |
-
"strip_accents":
|
13 |
"tokenize_chinese_chars": true,
|
14 |
"tokenizer_class": "BertTokenizer",
|
15 |
"unk_token": "[UNK]"
|
|
|
1 |
{
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
|
|
4 |
"do_lower_case": false,
|
5 |
"mask_token": "[MASK]",
|
|
|
6 |
"model_max_length": 512,
|
|
|
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]"
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|