Upload tokenizer.json
Browse files- tokenizer.json +75 -1
tokenizer.json
CHANGED
@@ -107,7 +107,81 @@
|
|
107 |
}
|
108 |
]
|
109 |
},
|
110 |
-
"post_processor":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
111 |
"decoder": null,
|
112 |
"model": {
|
113 |
"type": "WordPiece",
|
|
|
107 |
}
|
108 |
]
|
109 |
},
|
110 |
+
"post_processor": {
|
111 |
+
"type": "TemplateProcessing",
|
112 |
+
"single": [
|
113 |
+
{
|
114 |
+
"SpecialToken": {
|
115 |
+
"id": "[CLS]",
|
116 |
+
"type_id": 0
|
117 |
+
}
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"Sequence": {
|
121 |
+
"id": "A",
|
122 |
+
"type_id": 0
|
123 |
+
}
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"SpecialToken": {
|
127 |
+
"id": "[SEP]",
|
128 |
+
"type_id": 0
|
129 |
+
}
|
130 |
+
}
|
131 |
+
],
|
132 |
+
"pair": [
|
133 |
+
{
|
134 |
+
"SpecialToken": {
|
135 |
+
"id": "[CLS]",
|
136 |
+
"type_id": 0
|
137 |
+
}
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"Sequence": {
|
141 |
+
"id": "A",
|
142 |
+
"type_id": 0
|
143 |
+
}
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"SpecialToken": {
|
147 |
+
"id": "[SEP]",
|
148 |
+
"type_id": 0
|
149 |
+
}
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"Sequence": {
|
153 |
+
"id": "B",
|
154 |
+
"type_id": 1
|
155 |
+
}
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"SpecialToken": {
|
159 |
+
"id": "[SEP]",
|
160 |
+
"type_id": 1
|
161 |
+
}
|
162 |
+
}
|
163 |
+
],
|
164 |
+
"special_tokens": {
|
165 |
+
"[CLS]": {
|
166 |
+
"id": "[CLS]",
|
167 |
+
"ids": [
|
168 |
+
1
|
169 |
+
],
|
170 |
+
"tokens": [
|
171 |
+
"[CLS]"
|
172 |
+
]
|
173 |
+
},
|
174 |
+
"[SEP]": {
|
175 |
+
"id": "[SEP]",
|
176 |
+
"ids": [
|
177 |
+
2
|
178 |
+
],
|
179 |
+
"tokens": [
|
180 |
+
"[SEP]"
|
181 |
+
]
|
182 |
+
}
|
183 |
+
}
|
184 |
+
},
|
185 |
"decoder": null,
|
186 |
"model": {
|
187 |
"type": "WordPiece",
|