Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +8 -5
- vocab.txt +0 -0
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -8,7 +8,7 @@
|
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
-
"
|
| 12 |
"content": "[UNK]",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
|
@@ -16,7 +16,7 @@
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
"content": "[CLS]",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
@@ -24,7 +24,7 @@
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
-
"
|
| 28 |
"content": "[SEP]",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
|
@@ -32,7 +32,7 @@
|
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
"content": "[MASK]",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
|
@@ -43,12 +43,15 @@
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
|
|
|
| 46 |
"do_lower_case": false,
|
| 47 |
"mask_token": "[MASK]",
|
|
|
|
| 48 |
"model_max_length": 512,
|
|
|
|
| 49 |
"pad_token": "[PAD]",
|
| 50 |
"sep_token": "[SEP]",
|
| 51 |
-
"strip_accents":
|
| 52 |
"tokenize_chinese_chars": true,
|
| 53 |
"tokenizer_class": "BertTokenizer",
|
| 54 |
"unk_token": "[UNK]"
|
|
|
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
+
"1": {
|
| 12 |
"content": "[UNK]",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
|
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
+
"2": {
|
| 20 |
"content": "[CLS]",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
+
"3": {
|
| 28 |
"content": "[SEP]",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
|
|
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
+
"4": {
|
| 36 |
"content": "[MASK]",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
|
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": false,
|
| 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": false,
|
| 55 |
"tokenize_chinese_chars": true,
|
| 56 |
"tokenizer_class": "BertTokenizer",
|
| 57 |
"unk_token": "[UNK]"
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|