Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +155 -0
- tokenizer_config.json +18 -0
- vocab.txt +5 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "[CLS]",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "[SEP]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "[UNK]",
|
| 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": true,
|
| 56 |
+
"strip_accents": null,
|
| 57 |
+
"lowercase": false
|
| 58 |
+
},
|
| 59 |
+
"pre_tokenizer": {
|
| 60 |
+
"type": "BertPreTokenizer"
|
| 61 |
+
},
|
| 62 |
+
"post_processor": {
|
| 63 |
+
"type": "TemplateProcessing",
|
| 64 |
+
"single": [
|
| 65 |
+
{
|
| 66 |
+
"SpecialToken": {
|
| 67 |
+
"id": "[CLS]",
|
| 68 |
+
"type_id": 0
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"Sequence": {
|
| 73 |
+
"id": "A",
|
| 74 |
+
"type_id": 0
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"SpecialToken": {
|
| 79 |
+
"id": "[SEP]",
|
| 80 |
+
"type_id": 0
|
| 81 |
+
}
|
| 82 |
+
}
|
| 83 |
+
],
|
| 84 |
+
"pair": [
|
| 85 |
+
{
|
| 86 |
+
"SpecialToken": {
|
| 87 |
+
"id": "[CLS]",
|
| 88 |
+
"type_id": 0
|
| 89 |
+
}
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"Sequence": {
|
| 93 |
+
"id": "A",
|
| 94 |
+
"type_id": 0
|
| 95 |
+
}
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"SpecialToken": {
|
| 99 |
+
"id": "[SEP]",
|
| 100 |
+
"type_id": 0
|
| 101 |
+
}
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"Sequence": {
|
| 105 |
+
"id": "B",
|
| 106 |
+
"type_id": 0
|
| 107 |
+
}
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"SpecialToken": {
|
| 111 |
+
"id": "[SEP]",
|
| 112 |
+
"type_id": 0
|
| 113 |
+
}
|
| 114 |
+
}
|
| 115 |
+
],
|
| 116 |
+
"special_tokens": {
|
| 117 |
+
"[CLS]": {
|
| 118 |
+
"id": "[CLS]",
|
| 119 |
+
"ids": [
|
| 120 |
+
0
|
| 121 |
+
],
|
| 122 |
+
"tokens": [
|
| 123 |
+
"[CLS]"
|
| 124 |
+
]
|
| 125 |
+
},
|
| 126 |
+
"[SEP]": {
|
| 127 |
+
"id": "[SEP]",
|
| 128 |
+
"ids": [
|
| 129 |
+
2
|
| 130 |
+
],
|
| 131 |
+
"tokens": [
|
| 132 |
+
"[SEP]"
|
| 133 |
+
]
|
| 134 |
+
}
|
| 135 |
+
}
|
| 136 |
+
},
|
| 137 |
+
"decoder": {
|
| 138 |
+
"type": "WordPiece",
|
| 139 |
+
"prefix": "##",
|
| 140 |
+
"cleanup": true
|
| 141 |
+
},
|
| 142 |
+
"model": {
|
| 143 |
+
"type": "WordPiece",
|
| 144 |
+
"unk_token": "[UNK]",
|
| 145 |
+
"continuing_subword_prefix": "##",
|
| 146 |
+
"max_input_chars_per_word": 100,
|
| 147 |
+
"vocab": {
|
| 148 |
+
"[CLS]": 0,
|
| 149 |
+
"[PAD]": 1,
|
| 150 |
+
"[SEP]": 2,
|
| 151 |
+
"[UNK]": 3,
|
| 152 |
+
"[MASK]": 4
|
| 153 |
+
}
|
| 154 |
+
}
|
| 155 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"name_or_path": "klue/roberta-large",
|
| 10 |
+
"never_split": null,
|
| 11 |
+
"pad_token": "[PAD]",
|
| 12 |
+
"sep_token": "[SEP]",
|
| 13 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--klue--roberta-large/snapshots/5193b95701189160c45d02a1033a4ea55bdbe259/special_tokens_map.json",
|
| 14 |
+
"strip_accents": null,
|
| 15 |
+
"tokenize_chinese_chars": true,
|
| 16 |
+
"tokenizer_class": "BertTokenizer",
|
| 17 |
+
"unk_token": "[UNK]"
|
| 18 |
+
}
|
vocab.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[CLS]
|
| 2 |
+
[PAD]
|
| 3 |
+
[SEP]
|
| 4 |
+
[UNK]
|
| 5 |
+
[MASK]
|