Upload tokenizer
Browse files- tokenizer_config.json +3 -1
tokenizer_config.json
CHANGED
|
@@ -45,6 +45,7 @@
|
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
|
|
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"model_max_length": 512,
|
| 50 |
"never_split": null,
|
|
@@ -53,5 +54,6 @@
|
|
| 53 |
"strip_accents": null,
|
| 54 |
"tokenize_chinese_chars": true,
|
| 55 |
"tokenizer_class": "BertTokenizer",
|
| 56 |
-
"unk_token": "[UNK]"
|
|
|
|
| 57 |
}
|
|
|
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
"mask_token": "[MASK]",
|
| 50 |
"model_max_length": 512,
|
| 51 |
"never_split": null,
|
|
|
|
| 54 |
"strip_accents": null,
|
| 55 |
"tokenize_chinese_chars": true,
|
| 56 |
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"use_fast": true
|
| 59 |
}
|