Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +3 -2
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,10 +1,11 @@
|
|
| 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 |
-
"model_max_length":
|
| 8 |
"never_split": null,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
|
@@ -12,5 +13,5 @@
|
|
| 12 |
"tokenize_chinese_chars": true,
|
| 13 |
"tokenizer_class": "BertTokenizer",
|
| 14 |
"unk_token": "[UNK]",
|
| 15 |
-
"
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"clean_text": true,
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
"cls_token": "[CLS]",
|
| 5 |
"do_basic_tokenize": true,
|
| 6 |
"do_lower_case": false,
|
| 7 |
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
"never_split": null,
|
| 10 |
"pad_token": "[PAD]",
|
| 11 |
"sep_token": "[SEP]",
|
|
|
|
| 13 |
"tokenize_chinese_chars": true,
|
| 14 |
"tokenizer_class": "BertTokenizer",
|
| 15 |
"unk_token": "[UNK]",
|
| 16 |
+
"wordpieces_prefix": "##"
|
| 17 |
}
|