Update tokenizer_config.json
Browse files- tokenizer_config.json +256 -0
tokenizer_config.json
CHANGED
|
@@ -1114,6 +1114,246 @@
|
|
| 1114 |
"single_word": false,
|
| 1115 |
"special": false
|
| 1116 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1117 |
"169": {
|
| 1118 |
"content": "<table>",
|
| 1119 |
"lstrip": false,
|
|
@@ -1497,6 +1737,22 @@
|
|
| 1497 |
"rstrip": false,
|
| 1498 |
"single_word": false,
|
| 1499 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1500 |
}
|
| 1501 |
},
|
| 1502 |
"additional_special_tokens": [
|
|
|
|
| 1114 |
"single_word": false,
|
| 1115 |
"special": false
|
| 1116 |
},
|
| 1117 |
+
"139": {
|
| 1118 |
+
"content": "ββ",
|
| 1119 |
+
"lstrip": false,
|
| 1120 |
+
"normalized": false,
|
| 1121 |
+
"rstrip": false,
|
| 1122 |
+
"single_word": false,
|
| 1123 |
+
"special": false
|
| 1124 |
+
},
|
| 1125 |
+
"140": {
|
| 1126 |
+
"content": "βββ",
|
| 1127 |
+
"lstrip": false,
|
| 1128 |
+
"normalized": false,
|
| 1129 |
+
"rstrip": false,
|
| 1130 |
+
"single_word": false,
|
| 1131 |
+
"special": false
|
| 1132 |
+
},
|
| 1133 |
+
"141": {
|
| 1134 |
+
"content": "ββββ",
|
| 1135 |
+
"lstrip": false,
|
| 1136 |
+
"normalized": false,
|
| 1137 |
+
"rstrip": false,
|
| 1138 |
+
"single_word": false,
|
| 1139 |
+
"special": false
|
| 1140 |
+
},
|
| 1141 |
+
"142": {
|
| 1142 |
+
"content": "βββββ",
|
| 1143 |
+
"lstrip": false,
|
| 1144 |
+
"normalized": false,
|
| 1145 |
+
"rstrip": false,
|
| 1146 |
+
"single_word": false,
|
| 1147 |
+
"special": false
|
| 1148 |
+
},
|
| 1149 |
+
"143": {
|
| 1150 |
+
"content": "ββββββ",
|
| 1151 |
+
"lstrip": false,
|
| 1152 |
+
"normalized": false,
|
| 1153 |
+
"rstrip": false,
|
| 1154 |
+
"single_word": false,
|
| 1155 |
+
"special": false
|
| 1156 |
+
},
|
| 1157 |
+
"144": {
|
| 1158 |
+
"content": "βββββββ",
|
| 1159 |
+
"lstrip": false,
|
| 1160 |
+
"normalized": false,
|
| 1161 |
+
"rstrip": false,
|
| 1162 |
+
"single_word": false,
|
| 1163 |
+
"special": false
|
| 1164 |
+
},
|
| 1165 |
+
"145": {
|
| 1166 |
+
"content": "ββββββββ",
|
| 1167 |
+
"lstrip": false,
|
| 1168 |
+
"normalized": false,
|
| 1169 |
+
"rstrip": false,
|
| 1170 |
+
"single_word": false,
|
| 1171 |
+
"special": false
|
| 1172 |
+
},
|
| 1173 |
+
"146": {
|
| 1174 |
+
"content": "βββββββββ",
|
| 1175 |
+
"lstrip": false,
|
| 1176 |
+
"normalized": false,
|
| 1177 |
+
"rstrip": false,
|
| 1178 |
+
"single_word": false,
|
| 1179 |
+
"special": false
|
| 1180 |
+
},
|
| 1181 |
+
"147": {
|
| 1182 |
+
"content": "ββββββββββ",
|
| 1183 |
+
"lstrip": false,
|
| 1184 |
+
"normalized": false,
|
| 1185 |
+
"rstrip": false,
|
| 1186 |
+
"single_word": false,
|
| 1187 |
+
"special": false
|
| 1188 |
+
},
|
| 1189 |
+
"148": {
|
| 1190 |
+
"content": "βββββββββββ",
|
| 1191 |
+
"lstrip": false,
|
| 1192 |
+
"normalized": false,
|
| 1193 |
+
"rstrip": false,
|
| 1194 |
+
"single_word": false,
|
| 1195 |
+
"special": false
|
| 1196 |
+
},
|
| 1197 |
+
"149": {
|
| 1198 |
+
"content": "ββββββββββββ",
|
| 1199 |
+
"lstrip": false,
|
| 1200 |
+
"normalized": false,
|
| 1201 |
+
"rstrip": false,
|
| 1202 |
+
"single_word": false,
|
| 1203 |
+
"special": false
|
| 1204 |
+
},
|
| 1205 |
+
"150": {
|
| 1206 |
+
"content": "βββββββββββββ",
|
| 1207 |
+
"lstrip": false,
|
| 1208 |
+
"normalized": false,
|
| 1209 |
+
"rstrip": false,
|
| 1210 |
+
"single_word": false,
|
| 1211 |
+
"special": false
|
| 1212 |
+
},
|
| 1213 |
+
"151": {
|
| 1214 |
+
"content": "ββββββββββββββ",
|
| 1215 |
+
"lstrip": false,
|
| 1216 |
+
"normalized": false,
|
| 1217 |
+
"rstrip": false,
|
| 1218 |
+
"single_word": false,
|
| 1219 |
+
"special": false
|
| 1220 |
+
},
|
| 1221 |
+
"152": {
|
| 1222 |
+
"content": "βββββββββββββββ",
|
| 1223 |
+
"lstrip": false,
|
| 1224 |
+
"normalized": false,
|
| 1225 |
+
"rstrip": false,
|
| 1226 |
+
"single_word": false,
|
| 1227 |
+
"special": false
|
| 1228 |
+
},
|
| 1229 |
+
"153": {
|
| 1230 |
+
"content": "ββββββββββββββββ",
|
| 1231 |
+
"lstrip": false,
|
| 1232 |
+
"normalized": false,
|
| 1233 |
+
"rstrip": false,
|
| 1234 |
+
"single_word": false,
|
| 1235 |
+
"special": false
|
| 1236 |
+
},
|
| 1237 |
+
"154": {
|
| 1238 |
+
"content": "βββββββββββββββββ",
|
| 1239 |
+
"lstrip": false,
|
| 1240 |
+
"normalized": false,
|
| 1241 |
+
"rstrip": false,
|
| 1242 |
+
"single_word": false,
|
| 1243 |
+
"special": false
|
| 1244 |
+
},
|
| 1245 |
+
"155": {
|
| 1246 |
+
"content": "ββββββββββββββββββ",
|
| 1247 |
+
"lstrip": false,
|
| 1248 |
+
"normalized": false,
|
| 1249 |
+
"rstrip": false,
|
| 1250 |
+
"single_word": false,
|
| 1251 |
+
"special": false
|
| 1252 |
+
},
|
| 1253 |
+
"156": {
|
| 1254 |
+
"content": "βββββββββββββββββββ",
|
| 1255 |
+
"lstrip": false,
|
| 1256 |
+
"normalized": false,
|
| 1257 |
+
"rstrip": false,
|
| 1258 |
+
"single_word": false,
|
| 1259 |
+
"special": false
|
| 1260 |
+
},
|
| 1261 |
+
"157": {
|
| 1262 |
+
"content": "ββββββββββββββββββββ",
|
| 1263 |
+
"lstrip": false,
|
| 1264 |
+
"normalized": false,
|
| 1265 |
+
"rstrip": false,
|
| 1266 |
+
"single_word": false,
|
| 1267 |
+
"special": false
|
| 1268 |
+
},
|
| 1269 |
+
"158": {
|
| 1270 |
+
"content": "βββββββββββββββββββββ",
|
| 1271 |
+
"lstrip": false,
|
| 1272 |
+
"normalized": false,
|
| 1273 |
+
"rstrip": false,
|
| 1274 |
+
"single_word": false,
|
| 1275 |
+
"special": false
|
| 1276 |
+
},
|
| 1277 |
+
"159": {
|
| 1278 |
+
"content": "ββββββββββββββββββββββ",
|
| 1279 |
+
"lstrip": false,
|
| 1280 |
+
"normalized": false,
|
| 1281 |
+
"rstrip": false,
|
| 1282 |
+
"single_word": false,
|
| 1283 |
+
"special": false
|
| 1284 |
+
},
|
| 1285 |
+
"160": {
|
| 1286 |
+
"content": "βββββββββββββββββββββββ",
|
| 1287 |
+
"lstrip": false,
|
| 1288 |
+
"normalized": false,
|
| 1289 |
+
"rstrip": false,
|
| 1290 |
+
"single_word": false,
|
| 1291 |
+
"special": false
|
| 1292 |
+
},
|
| 1293 |
+
"161": {
|
| 1294 |
+
"content": "ββββββββββββββββββββββββ",
|
| 1295 |
+
"lstrip": false,
|
| 1296 |
+
"normalized": false,
|
| 1297 |
+
"rstrip": false,
|
| 1298 |
+
"single_word": false,
|
| 1299 |
+
"special": false
|
| 1300 |
+
},
|
| 1301 |
+
"162": {
|
| 1302 |
+
"content": "βββββββββββββββββββββββββ",
|
| 1303 |
+
"lstrip": false,
|
| 1304 |
+
"normalized": false,
|
| 1305 |
+
"rstrip": false,
|
| 1306 |
+
"single_word": false,
|
| 1307 |
+
"special": false
|
| 1308 |
+
},
|
| 1309 |
+
"163": {
|
| 1310 |
+
"content": "ββββββββββββββββββββββββββ",
|
| 1311 |
+
"lstrip": false,
|
| 1312 |
+
"normalized": false,
|
| 1313 |
+
"rstrip": false,
|
| 1314 |
+
"single_word": false,
|
| 1315 |
+
"special": false
|
| 1316 |
+
},
|
| 1317 |
+
"164": {
|
| 1318 |
+
"content": "βββββββββββββββββββββββββββ",
|
| 1319 |
+
"lstrip": false,
|
| 1320 |
+
"normalized": false,
|
| 1321 |
+
"rstrip": false,
|
| 1322 |
+
"single_word": false,
|
| 1323 |
+
"special": false
|
| 1324 |
+
},
|
| 1325 |
+
"165": {
|
| 1326 |
+
"content": "ββββββββββββββββββββββββββββ",
|
| 1327 |
+
"lstrip": false,
|
| 1328 |
+
"normalized": false,
|
| 1329 |
+
"rstrip": false,
|
| 1330 |
+
"single_word": false,
|
| 1331 |
+
"special": false
|
| 1332 |
+
},
|
| 1333 |
+
"166": {
|
| 1334 |
+
"content": "βββββββββββββββββββββββββββββ",
|
| 1335 |
+
"lstrip": false,
|
| 1336 |
+
"normalized": false,
|
| 1337 |
+
"rstrip": false,
|
| 1338 |
+
"single_word": false,
|
| 1339 |
+
"special": false
|
| 1340 |
+
},
|
| 1341 |
+
"167": {
|
| 1342 |
+
"content": "ββββββββββββββββββββββββββββββ",
|
| 1343 |
+
"lstrip": false,
|
| 1344 |
+
"normalized": false,
|
| 1345 |
+
"rstrip": false,
|
| 1346 |
+
"single_word": false,
|
| 1347 |
+
"special": false
|
| 1348 |
+
},
|
| 1349 |
+
"168": {
|
| 1350 |
+
"content": "βββββββββββββββββββββββββββββββ",
|
| 1351 |
+
"lstrip": false,
|
| 1352 |
+
"normalized": false,
|
| 1353 |
+
"rstrip": false,
|
| 1354 |
+
"single_word": false,
|
| 1355 |
+
"special": false
|
| 1356 |
+
},
|
| 1357 |
"169": {
|
| 1358 |
"content": "<table>",
|
| 1359 |
"lstrip": false,
|
|
|
|
| 1737 |
"rstrip": false,
|
| 1738 |
"single_word": false,
|
| 1739 |
"special": false
|
| 1740 |
+
},
|
| 1741 |
+
"256000": {
|
| 1742 |
+
"content": "<|im_start|>",
|
| 1743 |
+
"lstrip": false,
|
| 1744 |
+
"normalized": false,
|
| 1745 |
+
"rstrip": false,
|
| 1746 |
+
"single_word": false,
|
| 1747 |
+
"special": true
|
| 1748 |
+
},
|
| 1749 |
+
"256001": {
|
| 1750 |
+
"content": "<|im_end|>",
|
| 1751 |
+
"lstrip": false,
|
| 1752 |
+
"normalized": false,
|
| 1753 |
+
"rstrip": false,
|
| 1754 |
+
"single_word": false,
|
| 1755 |
+
"special": true
|
| 1756 |
}
|
| 1757 |
},
|
| 1758 |
"additional_special_tokens": [
|