Upload tokenizer
Browse files- special_tokens_map.json +14 -2
- tokenizer.json +10 -31
- tokenizer_config.json +5 -2
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,19 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
"cls_token": "[CLS]",
|
| 7 |
"mask_token": "[MASK]",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "[V0]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "[V1]",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
],
|
| 18 |
"cls_token": "[CLS]",
|
| 19 |
"mask_token": "[MASK]",
|
tokenizer.json
CHANGED
|
@@ -82,13 +82,7 @@
|
|
| 82 |
"single": [
|
| 83 |
{
|
| 84 |
"SpecialToken": {
|
| 85 |
-
"id": "[
|
| 86 |
-
"type_id": 0
|
| 87 |
-
}
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"SpecialToken": {
|
| 91 |
-
"id": "[V1]",
|
| 92 |
"type_id": 0
|
| 93 |
}
|
| 94 |
},
|
|
@@ -108,13 +102,7 @@
|
|
| 108 |
"pair": [
|
| 109 |
{
|
| 110 |
"SpecialToken": {
|
| 111 |
-
"id": "[
|
| 112 |
-
"type_id": 0
|
| 113 |
-
}
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"SpecialToken": {
|
| 117 |
-
"id": "[V1]",
|
| 118 |
"type_id": 0
|
| 119 |
}
|
| 120 |
},
|
|
@@ -144,31 +132,22 @@
|
|
| 144 |
}
|
| 145 |
],
|
| 146 |
"special_tokens": {
|
| 147 |
-
"[
|
| 148 |
-
"id": "[
|
| 149 |
"ids": [
|
| 150 |
-
|
| 151 |
],
|
| 152 |
"tokens": [
|
| 153 |
-
"[
|
| 154 |
]
|
| 155 |
},
|
| 156 |
-
"[
|
| 157 |
-
"id": "[
|
| 158 |
-
"ids": [
|
| 159 |
-
30522
|
| 160 |
-
],
|
| 161 |
-
"tokens": [
|
| 162 |
-
"[V0]"
|
| 163 |
-
]
|
| 164 |
-
},
|
| 165 |
-
"[V1]": {
|
| 166 |
-
"id": "[V1]",
|
| 167 |
"ids": [
|
| 168 |
-
|
| 169 |
],
|
| 170 |
"tokens": [
|
| 171 |
-
"[
|
| 172 |
]
|
| 173 |
}
|
| 174 |
}
|
|
|
|
| 82 |
"single": [
|
| 83 |
{
|
| 84 |
"SpecialToken": {
|
| 85 |
+
"id": "[CLS]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
"type_id": 0
|
| 87 |
}
|
| 88 |
},
|
|
|
|
| 102 |
"pair": [
|
| 103 |
{
|
| 104 |
"SpecialToken": {
|
| 105 |
+
"id": "[CLS]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 106 |
"type_id": 0
|
| 107 |
}
|
| 108 |
},
|
|
|
|
| 132 |
}
|
| 133 |
],
|
| 134 |
"special_tokens": {
|
| 135 |
+
"[CLS]": {
|
| 136 |
+
"id": "[CLS]",
|
| 137 |
"ids": [
|
| 138 |
+
101
|
| 139 |
],
|
| 140 |
"tokens": [
|
| 141 |
+
"[CLS]"
|
| 142 |
]
|
| 143 |
},
|
| 144 |
+
"[SEP]": {
|
| 145 |
+
"id": "[SEP]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146 |
"ids": [
|
| 147 |
+
102
|
| 148 |
],
|
| 149 |
"tokens": [
|
| 150 |
+
"[SEP]"
|
| 151 |
]
|
| 152 |
}
|
| 153 |
}
|
tokenizer_config.json
CHANGED
|
@@ -63,10 +63,13 @@
|
|
| 63 |
],
|
| 64 |
"clean_up_tokenization_spaces": true,
|
| 65 |
"cls_token": "[CLS]",
|
|
|
|
| 66 |
"mask_token": "[MASK]",
|
| 67 |
-
"model_max_length":
|
| 68 |
"pad_token": "[PAD]",
|
| 69 |
"sep_token": "[SEP]",
|
| 70 |
-
"
|
|
|
|
|
|
|
| 71 |
"unk_token": "[UNK]"
|
| 72 |
}
|
|
|
|
| 63 |
],
|
| 64 |
"clean_up_tokenization_spaces": true,
|
| 65 |
"cls_token": "[CLS]",
|
| 66 |
+
"do_lower_case": true,
|
| 67 |
"mask_token": "[MASK]",
|
| 68 |
+
"model_max_length": 512,
|
| 69 |
"pad_token": "[PAD]",
|
| 70 |
"sep_token": "[SEP]",
|
| 71 |
+
"strip_accents": null,
|
| 72 |
+
"tokenize_chinese_chars": true,
|
| 73 |
+
"tokenizer_class": "BertTokenizer",
|
| 74 |
"unk_token": "[UNK]"
|
| 75 |
}
|