Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +16 -88
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -73,7 +73,7 @@
|
|
| 73 |
"special": true
|
| 74 |
},
|
| 75 |
"9": {
|
| 76 |
-
"content": "[
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": false,
|
| 79 |
"rstrip": false,
|
|
@@ -81,7 +81,7 @@
|
|
| 81 |
"special": true
|
| 82 |
},
|
| 83 |
"10": {
|
| 84 |
-
"content": "[
|
| 85 |
"lstrip": false,
|
| 86 |
"normalized": false,
|
| 87 |
"rstrip": false,
|
|
@@ -89,7 +89,7 @@
|
|
| 89 |
"special": true
|
| 90 |
},
|
| 91 |
"11": {
|
| 92 |
-
"content": "[
|
| 93 |
"lstrip": false,
|
| 94 |
"normalized": false,
|
| 95 |
"rstrip": false,
|
|
@@ -97,7 +97,7 @@
|
|
| 97 |
"special": true
|
| 98 |
},
|
| 99 |
"12": {
|
| 100 |
-
"content": "[
|
| 101 |
"lstrip": false,
|
| 102 |
"normalized": false,
|
| 103 |
"rstrip": false,
|
|
@@ -105,7 +105,7 @@
|
|
| 105 |
"special": true
|
| 106 |
},
|
| 107 |
"13": {
|
| 108 |
-
"content": "[
|
| 109 |
"lstrip": false,
|
| 110 |
"normalized": false,
|
| 111 |
"rstrip": false,
|
|
@@ -113,7 +113,7 @@
|
|
| 113 |
"special": true
|
| 114 |
},
|
| 115 |
"14": {
|
| 116 |
-
"content": "[
|
| 117 |
"lstrip": false,
|
| 118 |
"normalized": false,
|
| 119 |
"rstrip": false,
|
|
@@ -121,7 +121,7 @@
|
|
| 121 |
"special": true
|
| 122 |
},
|
| 123 |
"15": {
|
| 124 |
-
"content": "[
|
| 125 |
"lstrip": false,
|
| 126 |
"normalized": false,
|
| 127 |
"rstrip": false,
|
|
@@ -129,7 +129,7 @@
|
|
| 129 |
"special": true
|
| 130 |
},
|
| 131 |
"16": {
|
| 132 |
-
"content": "[
|
| 133 |
"lstrip": false,
|
| 134 |
"normalized": false,
|
| 135 |
"rstrip": false,
|
|
@@ -137,7 +137,7 @@
|
|
| 137 |
"special": true
|
| 138 |
},
|
| 139 |
"17": {
|
| 140 |
-
"content": "[
|
| 141 |
"lstrip": false,
|
| 142 |
"normalized": false,
|
| 143 |
"rstrip": false,
|
|
@@ -145,7 +145,7 @@
|
|
| 145 |
"special": true
|
| 146 |
},
|
| 147 |
"18": {
|
| 148 |
-
"content": "[
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": false,
|
| 151 |
"rstrip": false,
|
|
@@ -153,7 +153,7 @@
|
|
| 153 |
"special": true
|
| 154 |
},
|
| 155 |
"19": {
|
| 156 |
-
"content": "[
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": false,
|
| 159 |
"rstrip": false,
|
|
@@ -161,7 +161,7 @@
|
|
| 161 |
"special": true
|
| 162 |
},
|
| 163 |
"20": {
|
| 164 |
-
"content": "[
|
| 165 |
"lstrip": false,
|
| 166 |
"normalized": false,
|
| 167 |
"rstrip": false,
|
|
@@ -169,7 +169,7 @@
|
|
| 169 |
"special": true
|
| 170 |
},
|
| 171 |
"21": {
|
| 172 |
-
"content": "[
|
| 173 |
"lstrip": false,
|
| 174 |
"normalized": false,
|
| 175 |
"rstrip": false,
|
|
@@ -177,7 +177,7 @@
|
|
| 177 |
"special": true
|
| 178 |
},
|
| 179 |
"22": {
|
| 180 |
-
"content": "[
|
| 181 |
"lstrip": false,
|
| 182 |
"normalized": false,
|
| 183 |
"rstrip": false,
|
|
@@ -185,7 +185,7 @@
|
|
| 185 |
"special": true
|
| 186 |
},
|
| 187 |
"23": {
|
| 188 |
-
"content": "[
|
| 189 |
"lstrip": false,
|
| 190 |
"normalized": false,
|
| 191 |
"rstrip": false,
|
|
@@ -193,79 +193,7 @@
|
|
| 193 |
"special": true
|
| 194 |
},
|
| 195 |
"24": {
|
| 196 |
-
"content": "[
|
| 197 |
-
"lstrip": false,
|
| 198 |
-
"normalized": false,
|
| 199 |
-
"rstrip": false,
|
| 200 |
-
"single_word": false,
|
| 201 |
-
"special": true
|
| 202 |
-
},
|
| 203 |
-
"25": {
|
| 204 |
-
"content": "[TECH]",
|
| 205 |
-
"lstrip": false,
|
| 206 |
-
"normalized": false,
|
| 207 |
-
"rstrip": false,
|
| 208 |
-
"single_word": false,
|
| 209 |
-
"special": true
|
| 210 |
-
},
|
| 211 |
-
"26": {
|
| 212 |
-
"content": "[MED]",
|
| 213 |
-
"lstrip": false,
|
| 214 |
-
"normalized": false,
|
| 215 |
-
"rstrip": false,
|
| 216 |
-
"single_word": false,
|
| 217 |
-
"special": true
|
| 218 |
-
},
|
| 219 |
-
"27": {
|
| 220 |
-
"content": "[LAW]",
|
| 221 |
-
"lstrip": false,
|
| 222 |
-
"normalized": false,
|
| 223 |
-
"rstrip": false,
|
| 224 |
-
"single_word": false,
|
| 225 |
-
"special": true
|
| 226 |
-
},
|
| 227 |
-
"28": {
|
| 228 |
-
"content": "[FINANCE]",
|
| 229 |
-
"lstrip": false,
|
| 230 |
-
"normalized": false,
|
| 231 |
-
"rstrip": false,
|
| 232 |
-
"single_word": false,
|
| 233 |
-
"special": true
|
| 234 |
-
},
|
| 235 |
-
"29": {
|
| 236 |
-
"content": "<num>",
|
| 237 |
-
"lstrip": false,
|
| 238 |
-
"normalized": false,
|
| 239 |
-
"rstrip": false,
|
| 240 |
-
"single_word": false,
|
| 241 |
-
"special": true
|
| 242 |
-
},
|
| 243 |
-
"30": {
|
| 244 |
-
"content": "<url>",
|
| 245 |
-
"lstrip": false,
|
| 246 |
-
"normalized": false,
|
| 247 |
-
"rstrip": false,
|
| 248 |
-
"single_word": false,
|
| 249 |
-
"special": true
|
| 250 |
-
},
|
| 251 |
-
"31": {
|
| 252 |
-
"content": "<email>",
|
| 253 |
-
"lstrip": false,
|
| 254 |
-
"normalized": false,
|
| 255 |
-
"rstrip": false,
|
| 256 |
-
"single_word": false,
|
| 257 |
-
"special": true
|
| 258 |
-
},
|
| 259 |
-
"32": {
|
| 260 |
-
"content": "<date>",
|
| 261 |
-
"lstrip": false,
|
| 262 |
-
"normalized": false,
|
| 263 |
-
"rstrip": false,
|
| 264 |
-
"single_word": false,
|
| 265 |
-
"special": true
|
| 266 |
-
},
|
| 267 |
-
"33": {
|
| 268 |
-
"content": "<time>",
|
| 269 |
"lstrip": false,
|
| 270 |
"normalized": false,
|
| 271 |
"rstrip": false,
|
|
|
|
| 73 |
"special": true
|
| 74 |
},
|
| 75 |
"9": {
|
| 76 |
+
"content": "[TITLE]",
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": false,
|
| 79 |
"rstrip": false,
|
|
|
|
| 81 |
"special": true
|
| 82 |
},
|
| 83 |
"10": {
|
| 84 |
+
"content": "[SECTION]",
|
| 85 |
"lstrip": false,
|
| 86 |
"normalized": false,
|
| 87 |
"rstrip": false,
|
|
|
|
| 89 |
"special": true
|
| 90 |
},
|
| 91 |
"11": {
|
| 92 |
+
"content": "[PARAGRAPH]",
|
| 93 |
"lstrip": false,
|
| 94 |
"normalized": false,
|
| 95 |
"rstrip": false,
|
|
|
|
| 97 |
"special": true
|
| 98 |
},
|
| 99 |
"12": {
|
| 100 |
+
"content": "[LIST]",
|
| 101 |
"lstrip": false,
|
| 102 |
"normalized": false,
|
| 103 |
"rstrip": false,
|
|
|
|
| 105 |
"special": true
|
| 106 |
},
|
| 107 |
"13": {
|
| 108 |
+
"content": "[QUOTE]",
|
| 109 |
"lstrip": false,
|
| 110 |
"normalized": false,
|
| 111 |
"rstrip": false,
|
|
|
|
| 113 |
"special": true
|
| 114 |
},
|
| 115 |
"14": {
|
| 116 |
+
"content": "[FR]",
|
| 117 |
"lstrip": false,
|
| 118 |
"normalized": false,
|
| 119 |
"rstrip": false,
|
|
|
|
| 121 |
"special": true
|
| 122 |
},
|
| 123 |
"15": {
|
| 124 |
+
"content": "[EN]",
|
| 125 |
"lstrip": false,
|
| 126 |
"normalized": false,
|
| 127 |
"rstrip": false,
|
|
|
|
| 129 |
"special": true
|
| 130 |
},
|
| 131 |
"16": {
|
| 132 |
+
"content": "[ES]",
|
| 133 |
"lstrip": false,
|
| 134 |
"normalized": false,
|
| 135 |
"rstrip": false,
|
|
|
|
| 137 |
"special": true
|
| 138 |
},
|
| 139 |
"17": {
|
| 140 |
+
"content": "[MATH]",
|
| 141 |
"lstrip": false,
|
| 142 |
"normalized": false,
|
| 143 |
"rstrip": false,
|
|
|
|
| 145 |
"special": true
|
| 146 |
},
|
| 147 |
"18": {
|
| 148 |
+
"content": "[SCIENCE]",
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": false,
|
| 151 |
"rstrip": false,
|
|
|
|
| 153 |
"special": true
|
| 154 |
},
|
| 155 |
"19": {
|
| 156 |
+
"content": "[HISTORY]",
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": false,
|
| 159 |
"rstrip": false,
|
|
|
|
| 161 |
"special": true
|
| 162 |
},
|
| 163 |
"20": {
|
| 164 |
+
"content": "[CITATION]",
|
| 165 |
"lstrip": false,
|
| 166 |
"normalized": false,
|
| 167 |
"rstrip": false,
|
|
|
|
| 169 |
"special": true
|
| 170 |
},
|
| 171 |
"21": {
|
| 172 |
+
"content": "[REFERENCE]",
|
| 173 |
"lstrip": false,
|
| 174 |
"normalized": false,
|
| 175 |
"rstrip": false,
|
|
|
|
| 177 |
"special": true
|
| 178 |
},
|
| 179 |
"22": {
|
| 180 |
+
"content": "[DATE]",
|
| 181 |
"lstrip": false,
|
| 182 |
"normalized": false,
|
| 183 |
"rstrip": false,
|
|
|
|
| 185 |
"special": true
|
| 186 |
},
|
| 187 |
"23": {
|
| 188 |
+
"content": "[LOCATION]",
|
| 189 |
"lstrip": false,
|
| 190 |
"normalized": false,
|
| 191 |
"rstrip": false,
|
|
|
|
| 193 |
"special": true
|
| 194 |
},
|
| 195 |
"24": {
|
| 196 |
+
"content": "[PERSON]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 197 |
"lstrip": false,
|
| 198 |
"normalized": false,
|
| 199 |
"rstrip": false,
|