Update tokenizer_config.json
Browse files- tokenizer_config.json +19 -1
tokenizer_config.json
CHANGED
|
@@ -23,16 +23,34 @@
|
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
},
|
| 28 |
"clean_up_tokenization_spaces": true,
|
| 29 |
"cls_token": "[CLS]",
|
| 30 |
"do_basic_tokenize": true,
|
| 31 |
"do_lower_case": true,
|
|
|
|
| 32 |
"max_len": 512,
|
| 33 |
"model_max_length": 512,
|
| 34 |
"never_split": null,
|
| 35 |
"pad_token": "[PAD]",
|
|
|
|
| 36 |
"strip_accents": null,
|
| 37 |
"tokenize_chinese_chars": true,
|
| 38 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
"max_len": 512,
|
| 50 |
"model_max_length": 512,
|
| 51 |
"never_split": null,
|
| 52 |
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
"strip_accents": null,
|
| 55 |
"tokenize_chinese_chars": true,
|
| 56 |
"tokenizer_class": "BertTokenizer",
|