Commit of multi-tokenizer for bmfm-omics
Browse files- tokenizers/expressions/special_tokens_map.json +37 -0
- tokenizers/expressions/tokenizer.json +201 -0
- tokenizers/expressions/tokenizer_config.json +59 -0
- tokenizers/expressions/vocab.json +1 -0
- tokenizers/genes/special_tokens_map.json +37 -0
- tokenizers/genes/tokenizer.json +0 -0
- tokenizers/genes/tokenizer_config.json +75 -0
- tokenizers/genes/vocab.json +0 -0
- tokenizers/label_expressions/special_tokens_map.json +37 -0
- tokenizers/label_expressions/tokenizer.json +201 -0
- tokenizers/label_expressions/tokenizer_config.json +59 -0
- tokenizers/label_expressions/vocab.json +1 -0
- tokenizers/perturbations/special_tokens_map.json +37 -0
- tokenizers/perturbations/tokenizer.json +153 -0
- tokenizers/perturbations/tokenizer_config.json +59 -0
- tokenizers/perturbations/vocab.json +1 -0
tokenizers/expressions/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 |
+
}
|
tokenizers/expressions/tokenizer.json
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "[UNK]",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "[PAD]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "[CLS]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "[MASK]",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
],
|
| 52 |
+
"normalizer": {
|
| 53 |
+
"type": "BertNormalizer",
|
| 54 |
+
"clean_text": true,
|
| 55 |
+
"handle_chinese_chars": false,
|
| 56 |
+
"strip_accents": null,
|
| 57 |
+
"lowercase": false
|
| 58 |
+
},
|
| 59 |
+
"pre_tokenizer": null,
|
| 60 |
+
"post_processor": {
|
| 61 |
+
"type": "TemplateProcessing",
|
| 62 |
+
"single": [
|
| 63 |
+
{
|
| 64 |
+
"SpecialToken": {
|
| 65 |
+
"id": "[CLS]",
|
| 66 |
+
"type_id": 0
|
| 67 |
+
}
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"Sequence": {
|
| 71 |
+
"id": "A",
|
| 72 |
+
"type_id": 0
|
| 73 |
+
}
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"SpecialToken": {
|
| 77 |
+
"id": "[SEP]",
|
| 78 |
+
"type_id": 0
|
| 79 |
+
}
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"pair": [
|
| 83 |
+
{
|
| 84 |
+
"SpecialToken": {
|
| 85 |
+
"id": "[CLS]",
|
| 86 |
+
"type_id": 0
|
| 87 |
+
}
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"Sequence": {
|
| 91 |
+
"id": "A",
|
| 92 |
+
"type_id": 0
|
| 93 |
+
}
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"SpecialToken": {
|
| 97 |
+
"id": "[SEP]",
|
| 98 |
+
"type_id": 0
|
| 99 |
+
}
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"Sequence": {
|
| 103 |
+
"id": "B",
|
| 104 |
+
"type_id": 1
|
| 105 |
+
}
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"SpecialToken": {
|
| 109 |
+
"id": "[SEP]",
|
| 110 |
+
"type_id": 1
|
| 111 |
+
}
|
| 112 |
+
}
|
| 113 |
+
],
|
| 114 |
+
"special_tokens": {
|
| 115 |
+
"[CLS]": {
|
| 116 |
+
"id": "[CLS]",
|
| 117 |
+
"ids": [
|
| 118 |
+
3
|
| 119 |
+
],
|
| 120 |
+
"tokens": [
|
| 121 |
+
"[CLS]"
|
| 122 |
+
]
|
| 123 |
+
},
|
| 124 |
+
"[SEP]": {
|
| 125 |
+
"id": "[SEP]",
|
| 126 |
+
"ids": [
|
| 127 |
+
1
|
| 128 |
+
],
|
| 129 |
+
"tokens": [
|
| 130 |
+
"[SEP]"
|
| 131 |
+
]
|
| 132 |
+
}
|
| 133 |
+
}
|
| 134 |
+
},
|
| 135 |
+
"decoder": {
|
| 136 |
+
"type": "WordPiece",
|
| 137 |
+
"prefix": "##",
|
| 138 |
+
"cleanup": true
|
| 139 |
+
},
|
| 140 |
+
"model": {
|
| 141 |
+
"type": "WordLevel",
|
| 142 |
+
"vocab": {
|
| 143 |
+
"[UNK]": 0,
|
| 144 |
+
"[SEP]": 1,
|
| 145 |
+
"[PAD]": 2,
|
| 146 |
+
"[CLS]": 3,
|
| 147 |
+
"[MASK]": 4,
|
| 148 |
+
"0": 5,
|
| 149 |
+
"1": 6,
|
| 150 |
+
"2": 7,
|
| 151 |
+
"3": 8,
|
| 152 |
+
"4": 9,
|
| 153 |
+
"5": 10,
|
| 154 |
+
"6": 11,
|
| 155 |
+
"7": 12,
|
| 156 |
+
"8": 13,
|
| 157 |
+
"9": 14,
|
| 158 |
+
"10": 15,
|
| 159 |
+
"11": 16,
|
| 160 |
+
"12": 17,
|
| 161 |
+
"13": 18,
|
| 162 |
+
"14": 19,
|
| 163 |
+
"15": 20,
|
| 164 |
+
"16": 21,
|
| 165 |
+
"17": 22,
|
| 166 |
+
"18": 23,
|
| 167 |
+
"19": 24,
|
| 168 |
+
"20": 25,
|
| 169 |
+
"21": 26,
|
| 170 |
+
"22": 27,
|
| 171 |
+
"23": 28,
|
| 172 |
+
"24": 29,
|
| 173 |
+
"25": 30,
|
| 174 |
+
"26": 31,
|
| 175 |
+
"27": 32,
|
| 176 |
+
"28": 33,
|
| 177 |
+
"29": 34,
|
| 178 |
+
"30": 35,
|
| 179 |
+
"31": 36,
|
| 180 |
+
"32": 37,
|
| 181 |
+
"33": 38,
|
| 182 |
+
"34": 39,
|
| 183 |
+
"35": 40,
|
| 184 |
+
"36": 41,
|
| 185 |
+
"37": 42,
|
| 186 |
+
"38": 43,
|
| 187 |
+
"39": 44,
|
| 188 |
+
"40": 45,
|
| 189 |
+
"41": 46,
|
| 190 |
+
"42": 47,
|
| 191 |
+
"43": 48,
|
| 192 |
+
"44": 49,
|
| 193 |
+
"45": 50,
|
| 194 |
+
"46": 51,
|
| 195 |
+
"47": 52,
|
| 196 |
+
"48": 53,
|
| 197 |
+
"49": 54
|
| 198 |
+
},
|
| 199 |
+
"unk_token": "[UNK]"
|
| 200 |
+
}
|
| 201 |
+
}
|
tokenizers/expressions/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[SEP]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[PAD]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[CLS]",
|
| 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_text": false,
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_basic_tokenize": true,
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": false,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
tokenizers/expressions/vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"[UNK]":0,"[SEP]":1,"[PAD]":2,"[CLS]":3,"[MASK]":4,"0":5,"1":6,"2":7,"3":8,"4":9,"5":10,"6":11,"7":12,"8":13,"9":14,"10":15,"11":16,"12":17,"13":18,"14":19,"15":20,"16":21,"17":22,"18":23,"19":24,"20":25,"21":26,"22":27,"23":28,"24":29,"25":30,"26":31,"27":32,"28":33,"29":34,"30":35,"31":36,"32":37,"33":38,"34":39,"35":40,"36":41,"37":42,"38":43,"39":44,"40":45,"41":46,"42":47,"43":48,"44":49,"45":50,"46":51,"47":52,"48":53,"49":54}
|
tokenizers/genes/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 |
+
}
|
tokenizers/genes/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizers/genes/tokenizer_config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[SEP]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[PAD]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[CLS]",
|
| 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 |
+
"94909": {
|
| 44 |
+
"content": "[S]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"94910": {
|
| 52 |
+
"content": "[T]",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"clean_text": false,
|
| 61 |
+
"clean_up_tokenization_spaces": true,
|
| 62 |
+
"cls_token": "[CLS]",
|
| 63 |
+
"do_basic_tokenize": true,
|
| 64 |
+
"do_lower_case": false,
|
| 65 |
+
"extra_special_tokens": {},
|
| 66 |
+
"mask_token": "[MASK]",
|
| 67 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 68 |
+
"never_split": null,
|
| 69 |
+
"pad_token": "[PAD]",
|
| 70 |
+
"sep_token": "[SEP]",
|
| 71 |
+
"strip_accents": null,
|
| 72 |
+
"tokenize_chinese_chars": false,
|
| 73 |
+
"tokenizer_class": "BertTokenizer",
|
| 74 |
+
"unk_token": "[UNK]"
|
| 75 |
+
}
|
tokenizers/genes/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizers/label_expressions/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 |
+
}
|
tokenizers/label_expressions/tokenizer.json
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "[UNK]",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "[PAD]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "[CLS]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "[MASK]",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
],
|
| 52 |
+
"normalizer": {
|
| 53 |
+
"type": "BertNormalizer",
|
| 54 |
+
"clean_text": true,
|
| 55 |
+
"handle_chinese_chars": false,
|
| 56 |
+
"strip_accents": null,
|
| 57 |
+
"lowercase": false
|
| 58 |
+
},
|
| 59 |
+
"pre_tokenizer": null,
|
| 60 |
+
"post_processor": {
|
| 61 |
+
"type": "TemplateProcessing",
|
| 62 |
+
"single": [
|
| 63 |
+
{
|
| 64 |
+
"SpecialToken": {
|
| 65 |
+
"id": "[CLS]",
|
| 66 |
+
"type_id": 0
|
| 67 |
+
}
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"Sequence": {
|
| 71 |
+
"id": "A",
|
| 72 |
+
"type_id": 0
|
| 73 |
+
}
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"SpecialToken": {
|
| 77 |
+
"id": "[SEP]",
|
| 78 |
+
"type_id": 0
|
| 79 |
+
}
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"pair": [
|
| 83 |
+
{
|
| 84 |
+
"SpecialToken": {
|
| 85 |
+
"id": "[CLS]",
|
| 86 |
+
"type_id": 0
|
| 87 |
+
}
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"Sequence": {
|
| 91 |
+
"id": "A",
|
| 92 |
+
"type_id": 0
|
| 93 |
+
}
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"SpecialToken": {
|
| 97 |
+
"id": "[SEP]",
|
| 98 |
+
"type_id": 0
|
| 99 |
+
}
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"Sequence": {
|
| 103 |
+
"id": "B",
|
| 104 |
+
"type_id": 1
|
| 105 |
+
}
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"SpecialToken": {
|
| 109 |
+
"id": "[SEP]",
|
| 110 |
+
"type_id": 1
|
| 111 |
+
}
|
| 112 |
+
}
|
| 113 |
+
],
|
| 114 |
+
"special_tokens": {
|
| 115 |
+
"[CLS]": {
|
| 116 |
+
"id": "[CLS]",
|
| 117 |
+
"ids": [
|
| 118 |
+
3
|
| 119 |
+
],
|
| 120 |
+
"tokens": [
|
| 121 |
+
"[CLS]"
|
| 122 |
+
]
|
| 123 |
+
},
|
| 124 |
+
"[SEP]": {
|
| 125 |
+
"id": "[SEP]",
|
| 126 |
+
"ids": [
|
| 127 |
+
1
|
| 128 |
+
],
|
| 129 |
+
"tokens": [
|
| 130 |
+
"[SEP]"
|
| 131 |
+
]
|
| 132 |
+
}
|
| 133 |
+
}
|
| 134 |
+
},
|
| 135 |
+
"decoder": {
|
| 136 |
+
"type": "WordPiece",
|
| 137 |
+
"prefix": "##",
|
| 138 |
+
"cleanup": true
|
| 139 |
+
},
|
| 140 |
+
"model": {
|
| 141 |
+
"type": "WordLevel",
|
| 142 |
+
"vocab": {
|
| 143 |
+
"[UNK]": 0,
|
| 144 |
+
"[SEP]": 1,
|
| 145 |
+
"[PAD]": 2,
|
| 146 |
+
"[CLS]": 3,
|
| 147 |
+
"[MASK]": 4,
|
| 148 |
+
"0": 5,
|
| 149 |
+
"1": 6,
|
| 150 |
+
"2": 7,
|
| 151 |
+
"3": 8,
|
| 152 |
+
"4": 9,
|
| 153 |
+
"5": 10,
|
| 154 |
+
"6": 11,
|
| 155 |
+
"7": 12,
|
| 156 |
+
"8": 13,
|
| 157 |
+
"9": 14,
|
| 158 |
+
"10": 15,
|
| 159 |
+
"11": 16,
|
| 160 |
+
"12": 17,
|
| 161 |
+
"13": 18,
|
| 162 |
+
"14": 19,
|
| 163 |
+
"15": 20,
|
| 164 |
+
"16": 21,
|
| 165 |
+
"17": 22,
|
| 166 |
+
"18": 23,
|
| 167 |
+
"19": 24,
|
| 168 |
+
"20": 25,
|
| 169 |
+
"21": 26,
|
| 170 |
+
"22": 27,
|
| 171 |
+
"23": 28,
|
| 172 |
+
"24": 29,
|
| 173 |
+
"25": 30,
|
| 174 |
+
"26": 31,
|
| 175 |
+
"27": 32,
|
| 176 |
+
"28": 33,
|
| 177 |
+
"29": 34,
|
| 178 |
+
"30": 35,
|
| 179 |
+
"31": 36,
|
| 180 |
+
"32": 37,
|
| 181 |
+
"33": 38,
|
| 182 |
+
"34": 39,
|
| 183 |
+
"35": 40,
|
| 184 |
+
"36": 41,
|
| 185 |
+
"37": 42,
|
| 186 |
+
"38": 43,
|
| 187 |
+
"39": 44,
|
| 188 |
+
"40": 45,
|
| 189 |
+
"41": 46,
|
| 190 |
+
"42": 47,
|
| 191 |
+
"43": 48,
|
| 192 |
+
"44": 49,
|
| 193 |
+
"45": 50,
|
| 194 |
+
"46": 51,
|
| 195 |
+
"47": 52,
|
| 196 |
+
"48": 53,
|
| 197 |
+
"49": 54
|
| 198 |
+
},
|
| 199 |
+
"unk_token": "[UNK]"
|
| 200 |
+
}
|
| 201 |
+
}
|
tokenizers/label_expressions/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[SEP]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[PAD]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[CLS]",
|
| 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_text": false,
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_basic_tokenize": true,
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": false,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
tokenizers/label_expressions/vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"[UNK]":0,"[SEP]":1,"[PAD]":2,"[CLS]":3,"[MASK]":4,"0":5,"1":6,"2":7,"3":8,"4":9,"5":10,"6":11,"7":12,"8":13,"9":14,"10":15,"11":16,"12":17,"13":18,"14":19,"15":20,"16":21,"17":22,"18":23,"19":24,"20":25,"21":26,"22":27,"23":28,"24":29,"25":30,"26":31,"27":32,"28":33,"29":34,"30":35,"31":36,"32":37,"33":38,"34":39,"35":40,"36":41,"37":42,"38":43,"39":44,"40":45,"41":46,"42":47,"43":48,"44":49,"45":50,"46":51,"47":52,"48":53,"49":54}
|
tokenizers/perturbations/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 |
+
}
|
tokenizers/perturbations/tokenizer.json
ADDED
|
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "[UNK]",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "[PAD]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "[CLS]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "[MASK]",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
],
|
| 52 |
+
"normalizer": {
|
| 53 |
+
"type": "BertNormalizer",
|
| 54 |
+
"clean_text": true,
|
| 55 |
+
"handle_chinese_chars": false,
|
| 56 |
+
"strip_accents": null,
|
| 57 |
+
"lowercase": false
|
| 58 |
+
},
|
| 59 |
+
"pre_tokenizer": null,
|
| 60 |
+
"post_processor": {
|
| 61 |
+
"type": "TemplateProcessing",
|
| 62 |
+
"single": [
|
| 63 |
+
{
|
| 64 |
+
"SpecialToken": {
|
| 65 |
+
"id": "[CLS]",
|
| 66 |
+
"type_id": 0
|
| 67 |
+
}
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"Sequence": {
|
| 71 |
+
"id": "A",
|
| 72 |
+
"type_id": 0
|
| 73 |
+
}
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"SpecialToken": {
|
| 77 |
+
"id": "[SEP]",
|
| 78 |
+
"type_id": 0
|
| 79 |
+
}
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"pair": [
|
| 83 |
+
{
|
| 84 |
+
"SpecialToken": {
|
| 85 |
+
"id": "[CLS]",
|
| 86 |
+
"type_id": 0
|
| 87 |
+
}
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"Sequence": {
|
| 91 |
+
"id": "A",
|
| 92 |
+
"type_id": 0
|
| 93 |
+
}
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"SpecialToken": {
|
| 97 |
+
"id": "[SEP]",
|
| 98 |
+
"type_id": 0
|
| 99 |
+
}
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"Sequence": {
|
| 103 |
+
"id": "B",
|
| 104 |
+
"type_id": 1
|
| 105 |
+
}
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"SpecialToken": {
|
| 109 |
+
"id": "[SEP]",
|
| 110 |
+
"type_id": 1
|
| 111 |
+
}
|
| 112 |
+
}
|
| 113 |
+
],
|
| 114 |
+
"special_tokens": {
|
| 115 |
+
"[CLS]": {
|
| 116 |
+
"id": "[CLS]",
|
| 117 |
+
"ids": [
|
| 118 |
+
3
|
| 119 |
+
],
|
| 120 |
+
"tokens": [
|
| 121 |
+
"[CLS]"
|
| 122 |
+
]
|
| 123 |
+
},
|
| 124 |
+
"[SEP]": {
|
| 125 |
+
"id": "[SEP]",
|
| 126 |
+
"ids": [
|
| 127 |
+
1
|
| 128 |
+
],
|
| 129 |
+
"tokens": [
|
| 130 |
+
"[SEP]"
|
| 131 |
+
]
|
| 132 |
+
}
|
| 133 |
+
}
|
| 134 |
+
},
|
| 135 |
+
"decoder": {
|
| 136 |
+
"type": "WordPiece",
|
| 137 |
+
"prefix": "##",
|
| 138 |
+
"cleanup": true
|
| 139 |
+
},
|
| 140 |
+
"model": {
|
| 141 |
+
"type": "WordLevel",
|
| 142 |
+
"vocab": {
|
| 143 |
+
"[UNK]": 0,
|
| 144 |
+
"[SEP]": 1,
|
| 145 |
+
"[PAD]": 2,
|
| 146 |
+
"[CLS]": 3,
|
| 147 |
+
"[MASK]": 4,
|
| 148 |
+
"0": 5,
|
| 149 |
+
"1": 6
|
| 150 |
+
},
|
| 151 |
+
"unk_token": "[UNK]"
|
| 152 |
+
}
|
| 153 |
+
}
|
tokenizers/perturbations/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[SEP]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[PAD]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[CLS]",
|
| 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_text": false,
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_basic_tokenize": true,
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": false,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
tokenizers/perturbations/vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"[UNK]":0,"[SEP]":1,"[PAD]":2,"[CLS]":3,"[MASK]":4,"0":5,"1":6}
|