Upload tokenizer for text classification
Browse files- added_tokens.json +7 -0
- special_tokens_map.json +37 -0
- tokenizer_config.json +97 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"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": 30523,
|
| 3 |
+
"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": 30524,
|
| 4 |
+
"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": 30525,
|
| 5 |
+
"7b0a2020202020202020202020202020202020202274696d657374616d70223a2072652e66696e64616c6c2872275c625c647b347d2d5c647b327d2d5c647b327d545c647b327d3a5c647b327d3a5c647b327d283f3a5c2e5c647b312c367d293f283f3a5b2b2d5d5c647b327d3a5c647b327d7c5a293f5c62272c206c6f675f6d657373616765295b305d2069662072652e66696e64616c6c2872275c625c647b347d2d5c647b327d2d5c647b327d545c647b327d3a5c647b327d3a5c647b327d283f3a5c2e5c647b312c367d293f283f3a5b2b2d5d5c647b327d3a5c647b327d7c5a293f5c62272c206c6f675f6d6573736167652920656c7365204e6f6e652c0a2020202020202020202020202020202022697022203a2072652e66696e64616c6c2872275c62283f3a5c647b312c337d5c2e297b337d5c647b312c337d5c62272c206c6f675f6d657373616765295b305d2069662072652e66696e64616c6c2872275c62283f3a5c647b312c337d5c2e297b337d5c647b312c337d5c62272c206c6f675f6d6573736167652920656c7365204e6f6e652c0a2020202020202020202020202020202020202275736572223a205b7320666f72207320696e2072652e66696e64616c6c287227283f3c3d5c7329285c532b29283f3d5c7329272c206c6f675f6d65737361676529206966206e6f7420626f6f6c2872652e7365617263682872275b5e5c775c735d272c207329295d5b305d206966205b7320666f72207320696e2072652e66696e64616c6c287227283f3c3d5c7329285c532b29283f3d5c7329272c206c6f675f6d65737361676529206966206e6f7420626f6f6c2872652e7365617263682872275b5e5c775c735d272c207329295d20656c7365204e6f6e652c0a202020202020202020202020202020202022616374696f6e22203a202772656e616d65272c0a20202020202020202020202020202022706174687322203a205b7061746820666f72206d6174636820696e2072652e66696e64616c6c2872275c7c282f5b5e7c225d2b29272c206c6f675f6d6573736167652920666f72207061746820696e205b6d617463685d206966206e6f742072652e7365617263682872275c647b347d2f5c647b327d2f5c647b327d205c647b327d3a5c647b327d3a5c647b327d272c2070617468295d0a0a20202020202020202020202020207d": 30522,
|
| 6 |
+
"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": 30526
|
| 7 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30522": {
|
| 44 |
+
"content": "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",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"30523": {
|
| 52 |
+
"content": "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",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"30524": {
|
| 60 |
+
"content": "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",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"30525": {
|
| 68 |
+
"content": "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",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"30526": {
|
| 76 |
+
"content": "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",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
}
|
| 83 |
+
},
|
| 84 |
+
"clean_up_tokenization_spaces": true,
|
| 85 |
+
"cls_token": "[CLS]",
|
| 86 |
+
"do_basic_tokenize": true,
|
| 87 |
+
"do_lower_case": true,
|
| 88 |
+
"mask_token": "[MASK]",
|
| 89 |
+
"model_max_length": 512,
|
| 90 |
+
"never_split": null,
|
| 91 |
+
"pad_token": "[PAD]",
|
| 92 |
+
"sep_token": "[SEP]",
|
| 93 |
+
"strip_accents": null,
|
| 94 |
+
"tokenize_chinese_chars": true,
|
| 95 |
+
"tokenizer_class": "BertTokenizer",
|
| 96 |
+
"unk_token": "[UNK]"
|
| 97 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|