CasperEriksen
commited on
Commit
·
ddff9d7
1
Parent(s):
9c53cf2
Update model using activity first input format
Browse files- README.md +3 -3
- config.json +103 -99
- pytorch_model.bin +2 -2
- tokenizer_config.json +1 -1
README.md
CHANGED
@@ -6,7 +6,7 @@ This model is [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) fine-t
|
|
6 |
## Data
|
7 |
Approximately 2.5 million business names and descriptions of activities from Norwegian and Danish businesses were used to fine-tune the model. The Norwegian descriptions were translated into Danish and the Norwegian SN 2007 codes were translated into Danish DB07 codes.
|
8 |
|
9 |
-
|
10 |
|
11 |
## Quick Start
|
12 |
|
@@ -23,7 +23,7 @@ pl = pipeline(
|
|
23 |
return_all_scores=False,
|
24 |
)
|
25 |
|
26 |
-
pl("
|
27 |
|
28 |
-
pl("
|
29 |
```
|
|
|
6 |
## Data
|
7 |
Approximately 2.5 million business names and descriptions of activities from Norwegian and Danish businesses were used to fine-tune the model. The Norwegian descriptions were translated into Danish and the Norwegian SN 2007 codes were translated into Danish DB07 codes.
|
8 |
|
9 |
+
Activity descriptions and business names were concatenated but separated by the separator token `</s>`. Thus, the model was trained on input texts in the format `f"{description_of_activity}</s>{business_name}"`.
|
10 |
|
11 |
## Quick Start
|
12 |
|
|
|
23 |
return_all_scores=False,
|
24 |
)
|
25 |
|
26 |
+
pl("Vi sælger sko")
|
27 |
|
28 |
+
pl("We sell clothes</s>Sneaker ApS")
|
29 |
```
|
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"XLMRobertaForSequenceClassification"
|
4 |
],
|
@@ -752,7 +753,104 @@
|
|
752 |
"label2id": {
|
753 |
"011100": 0,
|
754 |
"011200": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
755 |
"012400": 10,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
756 |
"139500": 100,
|
757 |
"139600": 101,
|
758 |
"139900": 102,
|
@@ -763,7 +861,6 @@
|
|
763 |
"141900": 107,
|
764 |
"142000": 108,
|
765 |
"143100": 109,
|
766 |
-
"012500": 11,
|
767 |
"143900": 110,
|
768 |
"151100": 111,
|
769 |
"151200": 112,
|
@@ -774,7 +871,6 @@
|
|
774 |
"162300": 117,
|
775 |
"162400": 118,
|
776 |
"162900": 119,
|
777 |
-
"012600": 12,
|
778 |
"171100": 120,
|
779 |
"171200": 121,
|
780 |
"172100": 122,
|
@@ -785,7 +881,6 @@
|
|
785 |
"181100": 127,
|
786 |
"181200": 128,
|
787 |
"181300": 129,
|
788 |
-
"012700": 13,
|
789 |
"181400": 130,
|
790 |
"182000": 131,
|
791 |
"191000": 132,
|
@@ -796,7 +891,6 @@
|
|
796 |
"201400": 137,
|
797 |
"201500": 138,
|
798 |
"201600": 139,
|
799 |
-
"012800": 14,
|
800 |
"201700": 140,
|
801 |
"202000": 141,
|
802 |
"203000": 142,
|
@@ -807,7 +901,6 @@
|
|
807 |
"205300": 147,
|
808 |
"205900": 148,
|
809 |
"206000": 149,
|
810 |
-
"012900": 15,
|
811 |
"211000": 150,
|
812 |
"212000": 151,
|
813 |
"221100": 152,
|
@@ -818,7 +911,6 @@
|
|
818 |
"222900": 157,
|
819 |
"231100": 158,
|
820 |
"231200": 159,
|
821 |
-
"013000": 16,
|
822 |
"231300": 160,
|
823 |
"231400": 161,
|
824 |
"231900": 162,
|
@@ -829,7 +921,6 @@
|
|
829 |
"234200": 167,
|
830 |
"234300": 168,
|
831 |
"234400": 169,
|
832 |
-
"014100": 17,
|
833 |
"234900": 170,
|
834 |
"235100": 171,
|
835 |
"235200": 172,
|
@@ -840,7 +931,6 @@
|
|
840 |
"236500": 177,
|
841 |
"236900": 178,
|
842 |
"237000": 179,
|
843 |
-
"014200": 18,
|
844 |
"239100": 180,
|
845 |
"239910": 181,
|
846 |
"239990": 182,
|
@@ -851,7 +941,6 @@
|
|
851 |
"243300": 187,
|
852 |
"243400": 188,
|
853 |
"244100": 189,
|
854 |
-
"014300": 19,
|
855 |
"244200": 190,
|
856 |
"244300": 191,
|
857 |
"244400": 192,
|
@@ -862,8 +951,6 @@
|
|
862 |
"245300": 197,
|
863 |
"245400": 198,
|
864 |
"251100": 199,
|
865 |
-
"011300": 2,
|
866 |
-
"014400": 20,
|
867 |
"251200": 200,
|
868 |
"252100": 201,
|
869 |
"252900": 202,
|
@@ -874,7 +961,6 @@
|
|
874 |
"256200": 207,
|
875 |
"257100": 208,
|
876 |
"257200": 209,
|
877 |
-
"014500": 21,
|
878 |
"257300": 210,
|
879 |
"259100": 211,
|
880 |
"259200": 212,
|
@@ -885,7 +971,6 @@
|
|
885 |
"261200": 217,
|
886 |
"262000": 218,
|
887 |
"263000": 219,
|
888 |
-
"014610": 22,
|
889 |
"264000": 220,
|
890 |
"265100": 221,
|
891 |
"265200": 222,
|
@@ -896,7 +981,6 @@
|
|
896 |
"271100": 227,
|
897 |
"271200": 228,
|
898 |
"272000": 229,
|
899 |
-
"014620": 23,
|
900 |
"273100": 230,
|
901 |
"273200": 231,
|
902 |
"273300": 232,
|
@@ -907,7 +991,6 @@
|
|
907 |
"281110": 237,
|
908 |
"281190": 238,
|
909 |
"281200": 239,
|
910 |
-
"014700": 24,
|
911 |
"281300": 240,
|
912 |
"281400": 241,
|
913 |
"281500": 242,
|
@@ -918,7 +1001,6 @@
|
|
918 |
"282500": 247,
|
919 |
"282900": 248,
|
920 |
"283000": 249,
|
921 |
-
"014910": 25,
|
922 |
"284100": 250,
|
923 |
"284900": 251,
|
924 |
"289100": 252,
|
@@ -929,7 +1011,6 @@
|
|
929 |
"289600": 257,
|
930 |
"289900": 258,
|
931 |
"291000": 259,
|
932 |
-
"014920": 26,
|
933 |
"292000": 260,
|
934 |
"293100": 261,
|
935 |
"293200": 262,
|
@@ -940,7 +1021,6 @@
|
|
940 |
"304000": 267,
|
941 |
"309100": 268,
|
942 |
"309200": 269,
|
943 |
-
"015000": 27,
|
944 |
"309900": 270,
|
945 |
"310100": 271,
|
946 |
"310200": 272,
|
@@ -951,7 +1031,6 @@
|
|
951 |
"321300": 277,
|
952 |
"322000": 278,
|
953 |
"323000": 279,
|
954 |
-
"016100": 28,
|
955 |
"324000": 280,
|
956 |
"325000": 281,
|
957 |
"329100": 282,
|
@@ -962,7 +1041,6 @@
|
|
962 |
"331400": 287,
|
963 |
"331500": 288,
|
964 |
"331600": 289,
|
965 |
-
"016200": 29,
|
966 |
"331700": 290,
|
967 |
"331900": 291,
|
968 |
"332000": 292,
|
@@ -973,8 +1051,6 @@
|
|
973 |
"352100": 297,
|
974 |
"352200": 298,
|
975 |
"352300": 299,
|
976 |
-
"011400": 3,
|
977 |
-
"016300": 30,
|
978 |
"353000": 300,
|
979 |
"360000": 301,
|
980 |
"370000": 302,
|
@@ -985,7 +1061,6 @@
|
|
985 |
"382200": 307,
|
986 |
"383100": 308,
|
987 |
"383200": 309,
|
988 |
-
"016400": 31,
|
989 |
"390000": 310,
|
990 |
"411000": 311,
|
991 |
"412000": 312,
|
@@ -996,7 +1071,6 @@
|
|
996 |
"422200": 317,
|
997 |
"429100": 318,
|
998 |
"429900": 319,
|
999 |
-
"017000": 32,
|
1000 |
"431100": 320,
|
1001 |
"431200": 321,
|
1002 |
"431300": 322,
|
@@ -1007,7 +1081,6 @@
|
|
1007 |
"433200": 327,
|
1008 |
"433300": 328,
|
1009 |
"433410": 329,
|
1010 |
-
"021000": 33,
|
1011 |
"433420": 330,
|
1012 |
"433900": 331,
|
1013 |
"439100": 332,
|
@@ -1018,7 +1091,6 @@
|
|
1018 |
"451910": 337,
|
1019 |
"451920": 338,
|
1020 |
"452010": 339,
|
1021 |
-
"022000": 34,
|
1022 |
"452020": 340,
|
1023 |
"452030": 341,
|
1024 |
"452040": 342,
|
@@ -1029,7 +1101,6 @@
|
|
1029 |
"461200": 347,
|
1030 |
"461300": 348,
|
1031 |
"461400": 349,
|
1032 |
-
"023000": 35,
|
1033 |
"461500": 350,
|
1034 |
"461600": 351,
|
1035 |
"461710": 352,
|
@@ -1040,7 +1111,6 @@
|
|
1040 |
"462200": 357,
|
1041 |
"462300": 358,
|
1042 |
"462400": 359,
|
1043 |
-
"024000": 36,
|
1044 |
"463100": 360,
|
1045 |
"463200": 361,
|
1046 |
"463300": 362,
|
@@ -1051,7 +1121,6 @@
|
|
1051 |
"463700": 367,
|
1052 |
"463810": 368,
|
1053 |
"463890": 369,
|
1054 |
-
"031100": 37,
|
1055 |
"463900": 370,
|
1056 |
"464100": 371,
|
1057 |
"464210": 372,
|
@@ -1062,7 +1131,6 @@
|
|
1062 |
"464340": 377,
|
1063 |
"464350": 378,
|
1064 |
"464410": 379,
|
1065 |
-
"031200": 38,
|
1066 |
"464420": 380,
|
1067 |
"464500": 381,
|
1068 |
"464610": 382,
|
@@ -1073,7 +1141,6 @@
|
|
1073 |
"464920": 387,
|
1074 |
"464930": 388,
|
1075 |
"464990": 389,
|
1076 |
-
"032100": 39,
|
1077 |
"465100": 390,
|
1078 |
"465210": 391,
|
1079 |
"465220": 392,
|
@@ -1084,8 +1151,6 @@
|
|
1084 |
"466500": 397,
|
1085 |
"466600": 398,
|
1086 |
"466900": 399,
|
1087 |
-
"011500": 4,
|
1088 |
-
"032200": 40,
|
1089 |
"467100": 400,
|
1090 |
"467200": 401,
|
1091 |
"467310": 402,
|
@@ -1096,7 +1161,6 @@
|
|
1096 |
"467700": 407,
|
1097 |
"469000": 408,
|
1098 |
"471110": 409,
|
1099 |
-
"051000": 41,
|
1100 |
"471120": 410,
|
1101 |
"471130": 411,
|
1102 |
"471900": 412,
|
@@ -1107,7 +1171,6 @@
|
|
1107 |
"472500": 417,
|
1108 |
"472600": 418,
|
1109 |
"472900": 419,
|
1110 |
-
"052000": 42,
|
1111 |
"473000": 420,
|
1112 |
"474100": 421,
|
1113 |
"474200": 422,
|
@@ -1118,7 +1181,6 @@
|
|
1118 |
"475300": 427,
|
1119 |
"475400": 428,
|
1120 |
"475910": 429,
|
1121 |
-
"061000": 43,
|
1122 |
"475920": 430,
|
1123 |
"475930": 431,
|
1124 |
"475940": 432,
|
@@ -1129,7 +1191,6 @@
|
|
1129 |
"476410": 437,
|
1130 |
"476420": 438,
|
1131 |
"476430": 439,
|
1132 |
-
"062000": 44,
|
1133 |
"476500": 440,
|
1134 |
"477110": 441,
|
1135 |
"477120": 442,
|
@@ -1140,7 +1201,6 @@
|
|
1140 |
"477500": 447,
|
1141 |
"477610": 448,
|
1142 |
"477620": 449,
|
1143 |
-
"071000": 45,
|
1144 |
"477630": 450,
|
1145 |
"477700": 451,
|
1146 |
"477810": 452,
|
@@ -1151,7 +1211,6 @@
|
|
1151 |
"477900": 457,
|
1152 |
"478100": 458,
|
1153 |
"478200": 459,
|
1154 |
-
"072100": 46,
|
1155 |
"478900": 460,
|
1156 |
"479111": 461,
|
1157 |
"479112": 462,
|
@@ -1162,7 +1221,6 @@
|
|
1162 |
"479117": 467,
|
1163 |
"479119": 468,
|
1164 |
"479120": 469,
|
1165 |
-
"072900": 47,
|
1166 |
"479900": 470,
|
1167 |
"491000": 471,
|
1168 |
"492000": 472,
|
@@ -1173,7 +1231,6 @@
|
|
1173 |
"493920": 477,
|
1174 |
"494100": 478,
|
1175 |
"494200": 479,
|
1176 |
-
"081100": 48,
|
1177 |
"495000": 480,
|
1178 |
"501000": 481,
|
1179 |
"502000": 482,
|
@@ -1184,7 +1241,6 @@
|
|
1184 |
"512100": 487,
|
1185 |
"512200": 488,
|
1186 |
"521000": 489,
|
1187 |
-
"081200": 49,
|
1188 |
"522110": 490,
|
1189 |
"522120": 491,
|
1190 |
"522130": 492,
|
@@ -1195,8 +1251,6 @@
|
|
1195 |
"522910": 497,
|
1196 |
"522920": 498,
|
1197 |
"522990": 499,
|
1198 |
-
"011600": 5,
|
1199 |
-
"089100": 50,
|
1200 |
"531000": 500,
|
1201 |
"532000": 501,
|
1202 |
"551010": 502,
|
@@ -1207,7 +1261,6 @@
|
|
1207 |
"561010": 507,
|
1208 |
"561020": 508,
|
1209 |
"562100": 509,
|
1210 |
-
"089200": 51,
|
1211 |
"562900": 510,
|
1212 |
"563000": 511,
|
1213 |
"581100": 512,
|
@@ -1218,7 +1271,6 @@
|
|
1218 |
"581900": 517,
|
1219 |
"582100": 518,
|
1220 |
"582900": 519,
|
1221 |
-
"089300": 52,
|
1222 |
"591110": 520,
|
1223 |
"591120": 521,
|
1224 |
"591200": 522,
|
@@ -1229,7 +1281,6 @@
|
|
1229 |
"602000": 527,
|
1230 |
"611000": 528,
|
1231 |
"612000": 529,
|
1232 |
-
"089900": 53,
|
1233 |
"613000": 530,
|
1234 |
"619000": 531,
|
1235 |
"620100": 532,
|
@@ -1240,7 +1291,6 @@
|
|
1240 |
"631200": 537,
|
1241 |
"639100": 538,
|
1242 |
"639900": 539,
|
1243 |
-
"091000": 54,
|
1244 |
"641100": 540,
|
1245 |
"641900": 541,
|
1246 |
"642010": 542,
|
@@ -1251,7 +1301,6 @@
|
|
1251 |
"643030": 547,
|
1252 |
"643040": 548,
|
1253 |
"649100": 549,
|
1254 |
-
"099000": 55,
|
1255 |
"649210": 550,
|
1256 |
"649220": 551,
|
1257 |
"649230": 552,
|
@@ -1262,7 +1311,6 @@
|
|
1262 |
"652000": 557,
|
1263 |
"653010": 558,
|
1264 |
"653020": 559,
|
1265 |
-
"101110": 56,
|
1266 |
"661100": 560,
|
1267 |
"661200": 561,
|
1268 |
"661900": 562,
|
@@ -1273,7 +1321,6 @@
|
|
1273 |
"681000": 567,
|
1274 |
"682010": 568,
|
1275 |
"682020": 569,
|
1276 |
-
"101190": 57,
|
1277 |
"682030": 570,
|
1278 |
"682040": 571,
|
1279 |
"683110": 572,
|
@@ -1284,7 +1331,6 @@
|
|
1284 |
"692000": 577,
|
1285 |
"701010": 578,
|
1286 |
"701020": 579,
|
1287 |
-
"101200": 58,
|
1288 |
"702100": 580,
|
1289 |
"702200": 581,
|
1290 |
"711100": 582,
|
@@ -1295,7 +1341,6 @@
|
|
1295 |
"711290": 587,
|
1296 |
"712010": 588,
|
1297 |
"712020": 589,
|
1298 |
-
"101300": 59,
|
1299 |
"712090": 590,
|
1300 |
"721100": 591,
|
1301 |
"721900": 592,
|
@@ -1306,8 +1351,6 @@
|
|
1306 |
"732000": 597,
|
1307 |
"741010": 598,
|
1308 |
"741020": 599,
|
1309 |
-
"011900": 6,
|
1310 |
-
"102010": 60,
|
1311 |
"741030": 600,
|
1312 |
"742000": 601,
|
1313 |
"743000": 602,
|
@@ -1318,7 +1361,6 @@
|
|
1318 |
"771200": 607,
|
1319 |
"772100": 608,
|
1320 |
"772200": 609,
|
1321 |
-
"102020": 61,
|
1322 |
"772900": 610,
|
1323 |
"773100": 611,
|
1324 |
"773200": 612,
|
@@ -1329,7 +1371,6 @@
|
|
1329 |
"774000": 617,
|
1330 |
"781000": 618,
|
1331 |
"782000": 619,
|
1332 |
-
"103100": 62,
|
1333 |
"783000": 620,
|
1334 |
"791100": 621,
|
1335 |
"791200": 622,
|
@@ -1340,7 +1381,6 @@
|
|
1340 |
"811000": 627,
|
1341 |
"812100": 628,
|
1342 |
"812210": 629,
|
1343 |
-
"103200": 63,
|
1344 |
"812220": 630,
|
1345 |
"812290": 631,
|
1346 |
"812900": 632,
|
@@ -1351,7 +1391,6 @@
|
|
1351 |
"823000": 637,
|
1352 |
"829100": 638,
|
1353 |
"829200": 639,
|
1354 |
-
"103900": 64,
|
1355 |
"829900": 640,
|
1356 |
"841100": 641,
|
1357 |
"841200": 642,
|
@@ -1362,7 +1401,6 @@
|
|
1362 |
"842400": 647,
|
1363 |
"842500": 648,
|
1364 |
"843000": 649,
|
1365 |
-
"104100": 65,
|
1366 |
"851000": 650,
|
1367 |
"852010": 651,
|
1368 |
"852020": 652,
|
@@ -1373,7 +1411,6 @@
|
|
1373 |
"854200": 657,
|
1374 |
"855100": 658,
|
1375 |
"855200": 659,
|
1376 |
-
"104200": 66,
|
1377 |
"855300": 660,
|
1378 |
"855900": 661,
|
1379 |
"856000": 662,
|
@@ -1384,7 +1421,6 @@
|
|
1384 |
"869010": 667,
|
1385 |
"869020": 668,
|
1386 |
"869030": 669,
|
1387 |
-
"105100": 67,
|
1388 |
"869040": 670,
|
1389 |
"869090": 671,
|
1390 |
"871010": 672,
|
@@ -1395,7 +1431,6 @@
|
|
1395 |
"873020": 677,
|
1396 |
"879010": 678,
|
1397 |
"879020": 679,
|
1398 |
-
"105200": 68,
|
1399 |
"879090": 680,
|
1400 |
"881010": 681,
|
1401 |
"881020": 682,
|
@@ -1406,7 +1441,6 @@
|
|
1406 |
"889140": 687,
|
1407 |
"889150": 688,
|
1408 |
"889160": 689,
|
1409 |
-
"106100": 69,
|
1410 |
"889910": 690,
|
1411 |
"889920": 691,
|
1412 |
"889990": 692,
|
@@ -1417,8 +1451,6 @@
|
|
1417 |
"900400": 697,
|
1418 |
"910110": 698,
|
1419 |
"910120": 699,
|
1420 |
-
"012100": 7,
|
1421 |
-
"106200": 70,
|
1422 |
"910200": 700,
|
1423 |
"910300": 701,
|
1424 |
"910400": 702,
|
@@ -1429,7 +1461,6 @@
|
|
1429 |
"931900": 707,
|
1430 |
"932100": 708,
|
1431 |
"932910": 709,
|
1432 |
-
"107110": 71,
|
1433 |
"932990": 710,
|
1434 |
"941100": 711,
|
1435 |
"941200": 712,
|
@@ -1440,7 +1471,6 @@
|
|
1440 |
"951100": 717,
|
1441 |
"951200": 718,
|
1442 |
"952100": 719,
|
1443 |
-
"107120": 72,
|
1444 |
"952200": 720,
|
1445 |
"952300": 721,
|
1446 |
"952400": 722,
|
@@ -1451,41 +1481,12 @@
|
|
1451 |
"960210": 727,
|
1452 |
"960220": 728,
|
1453 |
"960300": 729,
|
1454 |
-
"107200": 73,
|
1455 |
"960400": 730,
|
1456 |
"960900": 731,
|
1457 |
"970000": 732,
|
1458 |
"981000": 733,
|
1459 |
"982000": 734,
|
1460 |
-
"990000": 735
|
1461 |
-
"107300": 74,
|
1462 |
-
"108100": 75,
|
1463 |
-
"108200": 76,
|
1464 |
-
"108300": 77,
|
1465 |
-
"108400": 78,
|
1466 |
-
"108500": 79,
|
1467 |
-
"012200": 8,
|
1468 |
-
"108600": 80,
|
1469 |
-
"108900": 81,
|
1470 |
-
"109100": 82,
|
1471 |
-
"109200": 83,
|
1472 |
-
"110100": 84,
|
1473 |
-
"110200": 85,
|
1474 |
-
"110300": 86,
|
1475 |
-
"110400": 87,
|
1476 |
-
"110500": 88,
|
1477 |
-
"110600": 89,
|
1478 |
-
"012300": 9,
|
1479 |
-
"110700": 90,
|
1480 |
-
"120000": 91,
|
1481 |
-
"131000": 92,
|
1482 |
-
"132000": 93,
|
1483 |
-
"133000": 94,
|
1484 |
-
"139100": 95,
|
1485 |
-
"139210": 96,
|
1486 |
-
"139220": 97,
|
1487 |
-
"139300": 98,
|
1488 |
-
"139400": 99
|
1489 |
},
|
1490 |
"layer_norm_eps": 1e-05,
|
1491 |
"max_position_embeddings": 514,
|
@@ -1494,6 +1495,9 @@
|
|
1494 |
"num_hidden_layers": 12,
|
1495 |
"output_past": true,
|
1496 |
"pad_token_id": 1,
|
|
|
|
|
1497 |
"type_vocab_size": 1,
|
|
|
1498 |
"vocab_size": 250002
|
1499 |
-
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
"architectures": [
|
4 |
"XLMRobertaForSequenceClassification"
|
5 |
],
|
|
|
753 |
"label2id": {
|
754 |
"011100": 0,
|
755 |
"011200": 1,
|
756 |
+
"011300": 2,
|
757 |
+
"011400": 3,
|
758 |
+
"011500": 4,
|
759 |
+
"011600": 5,
|
760 |
+
"011900": 6,
|
761 |
+
"012100": 7,
|
762 |
+
"012200": 8,
|
763 |
+
"012300": 9,
|
764 |
"012400": 10,
|
765 |
+
"012500": 11,
|
766 |
+
"012600": 12,
|
767 |
+
"012700": 13,
|
768 |
+
"012800": 14,
|
769 |
+
"012900": 15,
|
770 |
+
"013000": 16,
|
771 |
+
"014100": 17,
|
772 |
+
"014200": 18,
|
773 |
+
"014300": 19,
|
774 |
+
"014400": 20,
|
775 |
+
"014500": 21,
|
776 |
+
"014610": 22,
|
777 |
+
"014620": 23,
|
778 |
+
"014700": 24,
|
779 |
+
"014910": 25,
|
780 |
+
"014920": 26,
|
781 |
+
"015000": 27,
|
782 |
+
"016100": 28,
|
783 |
+
"016200": 29,
|
784 |
+
"016300": 30,
|
785 |
+
"016400": 31,
|
786 |
+
"017000": 32,
|
787 |
+
"021000": 33,
|
788 |
+
"022000": 34,
|
789 |
+
"023000": 35,
|
790 |
+
"024000": 36,
|
791 |
+
"031100": 37,
|
792 |
+
"031200": 38,
|
793 |
+
"032100": 39,
|
794 |
+
"032200": 40,
|
795 |
+
"051000": 41,
|
796 |
+
"052000": 42,
|
797 |
+
"061000": 43,
|
798 |
+
"062000": 44,
|
799 |
+
"071000": 45,
|
800 |
+
"072100": 46,
|
801 |
+
"072900": 47,
|
802 |
+
"081100": 48,
|
803 |
+
"081200": 49,
|
804 |
+
"089100": 50,
|
805 |
+
"089200": 51,
|
806 |
+
"089300": 52,
|
807 |
+
"089900": 53,
|
808 |
+
"091000": 54,
|
809 |
+
"099000": 55,
|
810 |
+
"101110": 56,
|
811 |
+
"101190": 57,
|
812 |
+
"101200": 58,
|
813 |
+
"101300": 59,
|
814 |
+
"102010": 60,
|
815 |
+
"102020": 61,
|
816 |
+
"103100": 62,
|
817 |
+
"103200": 63,
|
818 |
+
"103900": 64,
|
819 |
+
"104100": 65,
|
820 |
+
"104200": 66,
|
821 |
+
"105100": 67,
|
822 |
+
"105200": 68,
|
823 |
+
"106100": 69,
|
824 |
+
"106200": 70,
|
825 |
+
"107110": 71,
|
826 |
+
"107120": 72,
|
827 |
+
"107200": 73,
|
828 |
+
"107300": 74,
|
829 |
+
"108100": 75,
|
830 |
+
"108200": 76,
|
831 |
+
"108300": 77,
|
832 |
+
"108400": 78,
|
833 |
+
"108500": 79,
|
834 |
+
"108600": 80,
|
835 |
+
"108900": 81,
|
836 |
+
"109100": 82,
|
837 |
+
"109200": 83,
|
838 |
+
"110100": 84,
|
839 |
+
"110200": 85,
|
840 |
+
"110300": 86,
|
841 |
+
"110400": 87,
|
842 |
+
"110500": 88,
|
843 |
+
"110600": 89,
|
844 |
+
"110700": 90,
|
845 |
+
"120000": 91,
|
846 |
+
"131000": 92,
|
847 |
+
"132000": 93,
|
848 |
+
"133000": 94,
|
849 |
+
"139100": 95,
|
850 |
+
"139210": 96,
|
851 |
+
"139220": 97,
|
852 |
+
"139300": 98,
|
853 |
+
"139400": 99,
|
854 |
"139500": 100,
|
855 |
"139600": 101,
|
856 |
"139900": 102,
|
|
|
861 |
"141900": 107,
|
862 |
"142000": 108,
|
863 |
"143100": 109,
|
|
|
864 |
"143900": 110,
|
865 |
"151100": 111,
|
866 |
"151200": 112,
|
|
|
871 |
"162300": 117,
|
872 |
"162400": 118,
|
873 |
"162900": 119,
|
|
|
874 |
"171100": 120,
|
875 |
"171200": 121,
|
876 |
"172100": 122,
|
|
|
881 |
"181100": 127,
|
882 |
"181200": 128,
|
883 |
"181300": 129,
|
|
|
884 |
"181400": 130,
|
885 |
"182000": 131,
|
886 |
"191000": 132,
|
|
|
891 |
"201400": 137,
|
892 |
"201500": 138,
|
893 |
"201600": 139,
|
|
|
894 |
"201700": 140,
|
895 |
"202000": 141,
|
896 |
"203000": 142,
|
|
|
901 |
"205300": 147,
|
902 |
"205900": 148,
|
903 |
"206000": 149,
|
|
|
904 |
"211000": 150,
|
905 |
"212000": 151,
|
906 |
"221100": 152,
|
|
|
911 |
"222900": 157,
|
912 |
"231100": 158,
|
913 |
"231200": 159,
|
|
|
914 |
"231300": 160,
|
915 |
"231400": 161,
|
916 |
"231900": 162,
|
|
|
921 |
"234200": 167,
|
922 |
"234300": 168,
|
923 |
"234400": 169,
|
|
|
924 |
"234900": 170,
|
925 |
"235100": 171,
|
926 |
"235200": 172,
|
|
|
931 |
"236500": 177,
|
932 |
"236900": 178,
|
933 |
"237000": 179,
|
|
|
934 |
"239100": 180,
|
935 |
"239910": 181,
|
936 |
"239990": 182,
|
|
|
941 |
"243300": 187,
|
942 |
"243400": 188,
|
943 |
"244100": 189,
|
|
|
944 |
"244200": 190,
|
945 |
"244300": 191,
|
946 |
"244400": 192,
|
|
|
951 |
"245300": 197,
|
952 |
"245400": 198,
|
953 |
"251100": 199,
|
|
|
|
|
954 |
"251200": 200,
|
955 |
"252100": 201,
|
956 |
"252900": 202,
|
|
|
961 |
"256200": 207,
|
962 |
"257100": 208,
|
963 |
"257200": 209,
|
|
|
964 |
"257300": 210,
|
965 |
"259100": 211,
|
966 |
"259200": 212,
|
|
|
971 |
"261200": 217,
|
972 |
"262000": 218,
|
973 |
"263000": 219,
|
|
|
974 |
"264000": 220,
|
975 |
"265100": 221,
|
976 |
"265200": 222,
|
|
|
981 |
"271100": 227,
|
982 |
"271200": 228,
|
983 |
"272000": 229,
|
|
|
984 |
"273100": 230,
|
985 |
"273200": 231,
|
986 |
"273300": 232,
|
|
|
991 |
"281110": 237,
|
992 |
"281190": 238,
|
993 |
"281200": 239,
|
|
|
994 |
"281300": 240,
|
995 |
"281400": 241,
|
996 |
"281500": 242,
|
|
|
1001 |
"282500": 247,
|
1002 |
"282900": 248,
|
1003 |
"283000": 249,
|
|
|
1004 |
"284100": 250,
|
1005 |
"284900": 251,
|
1006 |
"289100": 252,
|
|
|
1011 |
"289600": 257,
|
1012 |
"289900": 258,
|
1013 |
"291000": 259,
|
|
|
1014 |
"292000": 260,
|
1015 |
"293100": 261,
|
1016 |
"293200": 262,
|
|
|
1021 |
"304000": 267,
|
1022 |
"309100": 268,
|
1023 |
"309200": 269,
|
|
|
1024 |
"309900": 270,
|
1025 |
"310100": 271,
|
1026 |
"310200": 272,
|
|
|
1031 |
"321300": 277,
|
1032 |
"322000": 278,
|
1033 |
"323000": 279,
|
|
|
1034 |
"324000": 280,
|
1035 |
"325000": 281,
|
1036 |
"329100": 282,
|
|
|
1041 |
"331400": 287,
|
1042 |
"331500": 288,
|
1043 |
"331600": 289,
|
|
|
1044 |
"331700": 290,
|
1045 |
"331900": 291,
|
1046 |
"332000": 292,
|
|
|
1051 |
"352100": 297,
|
1052 |
"352200": 298,
|
1053 |
"352300": 299,
|
|
|
|
|
1054 |
"353000": 300,
|
1055 |
"360000": 301,
|
1056 |
"370000": 302,
|
|
|
1061 |
"382200": 307,
|
1062 |
"383100": 308,
|
1063 |
"383200": 309,
|
|
|
1064 |
"390000": 310,
|
1065 |
"411000": 311,
|
1066 |
"412000": 312,
|
|
|
1071 |
"422200": 317,
|
1072 |
"429100": 318,
|
1073 |
"429900": 319,
|
|
|
1074 |
"431100": 320,
|
1075 |
"431200": 321,
|
1076 |
"431300": 322,
|
|
|
1081 |
"433200": 327,
|
1082 |
"433300": 328,
|
1083 |
"433410": 329,
|
|
|
1084 |
"433420": 330,
|
1085 |
"433900": 331,
|
1086 |
"439100": 332,
|
|
|
1091 |
"451910": 337,
|
1092 |
"451920": 338,
|
1093 |
"452010": 339,
|
|
|
1094 |
"452020": 340,
|
1095 |
"452030": 341,
|
1096 |
"452040": 342,
|
|
|
1101 |
"461200": 347,
|
1102 |
"461300": 348,
|
1103 |
"461400": 349,
|
|
|
1104 |
"461500": 350,
|
1105 |
"461600": 351,
|
1106 |
"461710": 352,
|
|
|
1111 |
"462200": 357,
|
1112 |
"462300": 358,
|
1113 |
"462400": 359,
|
|
|
1114 |
"463100": 360,
|
1115 |
"463200": 361,
|
1116 |
"463300": 362,
|
|
|
1121 |
"463700": 367,
|
1122 |
"463810": 368,
|
1123 |
"463890": 369,
|
|
|
1124 |
"463900": 370,
|
1125 |
"464100": 371,
|
1126 |
"464210": 372,
|
|
|
1131 |
"464340": 377,
|
1132 |
"464350": 378,
|
1133 |
"464410": 379,
|
|
|
1134 |
"464420": 380,
|
1135 |
"464500": 381,
|
1136 |
"464610": 382,
|
|
|
1141 |
"464920": 387,
|
1142 |
"464930": 388,
|
1143 |
"464990": 389,
|
|
|
1144 |
"465100": 390,
|
1145 |
"465210": 391,
|
1146 |
"465220": 392,
|
|
|
1151 |
"466500": 397,
|
1152 |
"466600": 398,
|
1153 |
"466900": 399,
|
|
|
|
|
1154 |
"467100": 400,
|
1155 |
"467200": 401,
|
1156 |
"467310": 402,
|
|
|
1161 |
"467700": 407,
|
1162 |
"469000": 408,
|
1163 |
"471110": 409,
|
|
|
1164 |
"471120": 410,
|
1165 |
"471130": 411,
|
1166 |
"471900": 412,
|
|
|
1171 |
"472500": 417,
|
1172 |
"472600": 418,
|
1173 |
"472900": 419,
|
|
|
1174 |
"473000": 420,
|
1175 |
"474100": 421,
|
1176 |
"474200": 422,
|
|
|
1181 |
"475300": 427,
|
1182 |
"475400": 428,
|
1183 |
"475910": 429,
|
|
|
1184 |
"475920": 430,
|
1185 |
"475930": 431,
|
1186 |
"475940": 432,
|
|
|
1191 |
"476410": 437,
|
1192 |
"476420": 438,
|
1193 |
"476430": 439,
|
|
|
1194 |
"476500": 440,
|
1195 |
"477110": 441,
|
1196 |
"477120": 442,
|
|
|
1201 |
"477500": 447,
|
1202 |
"477610": 448,
|
1203 |
"477620": 449,
|
|
|
1204 |
"477630": 450,
|
1205 |
"477700": 451,
|
1206 |
"477810": 452,
|
|
|
1211 |
"477900": 457,
|
1212 |
"478100": 458,
|
1213 |
"478200": 459,
|
|
|
1214 |
"478900": 460,
|
1215 |
"479111": 461,
|
1216 |
"479112": 462,
|
|
|
1221 |
"479117": 467,
|
1222 |
"479119": 468,
|
1223 |
"479120": 469,
|
|
|
1224 |
"479900": 470,
|
1225 |
"491000": 471,
|
1226 |
"492000": 472,
|
|
|
1231 |
"493920": 477,
|
1232 |
"494100": 478,
|
1233 |
"494200": 479,
|
|
|
1234 |
"495000": 480,
|
1235 |
"501000": 481,
|
1236 |
"502000": 482,
|
|
|
1241 |
"512100": 487,
|
1242 |
"512200": 488,
|
1243 |
"521000": 489,
|
|
|
1244 |
"522110": 490,
|
1245 |
"522120": 491,
|
1246 |
"522130": 492,
|
|
|
1251 |
"522910": 497,
|
1252 |
"522920": 498,
|
1253 |
"522990": 499,
|
|
|
|
|
1254 |
"531000": 500,
|
1255 |
"532000": 501,
|
1256 |
"551010": 502,
|
|
|
1261 |
"561010": 507,
|
1262 |
"561020": 508,
|
1263 |
"562100": 509,
|
|
|
1264 |
"562900": 510,
|
1265 |
"563000": 511,
|
1266 |
"581100": 512,
|
|
|
1271 |
"581900": 517,
|
1272 |
"582100": 518,
|
1273 |
"582900": 519,
|
|
|
1274 |
"591110": 520,
|
1275 |
"591120": 521,
|
1276 |
"591200": 522,
|
|
|
1281 |
"602000": 527,
|
1282 |
"611000": 528,
|
1283 |
"612000": 529,
|
|
|
1284 |
"613000": 530,
|
1285 |
"619000": 531,
|
1286 |
"620100": 532,
|
|
|
1291 |
"631200": 537,
|
1292 |
"639100": 538,
|
1293 |
"639900": 539,
|
|
|
1294 |
"641100": 540,
|
1295 |
"641900": 541,
|
1296 |
"642010": 542,
|
|
|
1301 |
"643030": 547,
|
1302 |
"643040": 548,
|
1303 |
"649100": 549,
|
|
|
1304 |
"649210": 550,
|
1305 |
"649220": 551,
|
1306 |
"649230": 552,
|
|
|
1311 |
"652000": 557,
|
1312 |
"653010": 558,
|
1313 |
"653020": 559,
|
|
|
1314 |
"661100": 560,
|
1315 |
"661200": 561,
|
1316 |
"661900": 562,
|
|
|
1321 |
"681000": 567,
|
1322 |
"682010": 568,
|
1323 |
"682020": 569,
|
|
|
1324 |
"682030": 570,
|
1325 |
"682040": 571,
|
1326 |
"683110": 572,
|
|
|
1331 |
"692000": 577,
|
1332 |
"701010": 578,
|
1333 |
"701020": 579,
|
|
|
1334 |
"702100": 580,
|
1335 |
"702200": 581,
|
1336 |
"711100": 582,
|
|
|
1341 |
"711290": 587,
|
1342 |
"712010": 588,
|
1343 |
"712020": 589,
|
|
|
1344 |
"712090": 590,
|
1345 |
"721100": 591,
|
1346 |
"721900": 592,
|
|
|
1351 |
"732000": 597,
|
1352 |
"741010": 598,
|
1353 |
"741020": 599,
|
|
|
|
|
1354 |
"741030": 600,
|
1355 |
"742000": 601,
|
1356 |
"743000": 602,
|
|
|
1361 |
"771200": 607,
|
1362 |
"772100": 608,
|
1363 |
"772200": 609,
|
|
|
1364 |
"772900": 610,
|
1365 |
"773100": 611,
|
1366 |
"773200": 612,
|
|
|
1371 |
"774000": 617,
|
1372 |
"781000": 618,
|
1373 |
"782000": 619,
|
|
|
1374 |
"783000": 620,
|
1375 |
"791100": 621,
|
1376 |
"791200": 622,
|
|
|
1381 |
"811000": 627,
|
1382 |
"812100": 628,
|
1383 |
"812210": 629,
|
|
|
1384 |
"812220": 630,
|
1385 |
"812290": 631,
|
1386 |
"812900": 632,
|
|
|
1391 |
"823000": 637,
|
1392 |
"829100": 638,
|
1393 |
"829200": 639,
|
|
|
1394 |
"829900": 640,
|
1395 |
"841100": 641,
|
1396 |
"841200": 642,
|
|
|
1401 |
"842400": 647,
|
1402 |
"842500": 648,
|
1403 |
"843000": 649,
|
|
|
1404 |
"851000": 650,
|
1405 |
"852010": 651,
|
1406 |
"852020": 652,
|
|
|
1411 |
"854200": 657,
|
1412 |
"855100": 658,
|
1413 |
"855200": 659,
|
|
|
1414 |
"855300": 660,
|
1415 |
"855900": 661,
|
1416 |
"856000": 662,
|
|
|
1421 |
"869010": 667,
|
1422 |
"869020": 668,
|
1423 |
"869030": 669,
|
|
|
1424 |
"869040": 670,
|
1425 |
"869090": 671,
|
1426 |
"871010": 672,
|
|
|
1431 |
"873020": 677,
|
1432 |
"879010": 678,
|
1433 |
"879020": 679,
|
|
|
1434 |
"879090": 680,
|
1435 |
"881010": 681,
|
1436 |
"881020": 682,
|
|
|
1441 |
"889140": 687,
|
1442 |
"889150": 688,
|
1443 |
"889160": 689,
|
|
|
1444 |
"889910": 690,
|
1445 |
"889920": 691,
|
1446 |
"889990": 692,
|
|
|
1451 |
"900400": 697,
|
1452 |
"910110": 698,
|
1453 |
"910120": 699,
|
|
|
|
|
1454 |
"910200": 700,
|
1455 |
"910300": 701,
|
1456 |
"910400": 702,
|
|
|
1461 |
"931900": 707,
|
1462 |
"932100": 708,
|
1463 |
"932910": 709,
|
|
|
1464 |
"932990": 710,
|
1465 |
"941100": 711,
|
1466 |
"941200": 712,
|
|
|
1471 |
"951100": 717,
|
1472 |
"951200": 718,
|
1473 |
"952100": 719,
|
|
|
1474 |
"952200": 720,
|
1475 |
"952300": 721,
|
1476 |
"952400": 722,
|
|
|
1481 |
"960210": 727,
|
1482 |
"960220": 728,
|
1483 |
"960300": 729,
|
|
|
1484 |
"960400": 730,
|
1485 |
"960900": 731,
|
1486 |
"970000": 732,
|
1487 |
"981000": 733,
|
1488 |
"982000": 734,
|
1489 |
+
"990000": 735
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1490 |
},
|
1491 |
"layer_norm_eps": 1e-05,
|
1492 |
"max_position_embeddings": 514,
|
|
|
1495 |
"num_hidden_layers": 12,
|
1496 |
"output_past": true,
|
1497 |
"pad_token_id": 1,
|
1498 |
+
"position_embedding_type": "absolute",
|
1499 |
+
"transformers_version": "4.2.1",
|
1500 |
"type_vocab_size": 1,
|
1501 |
+
"use_cache": true,
|
1502 |
"vocab_size": 250002
|
1503 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c123a59b1138fa303e1580bf59839dba48d6d61e84a621e0437a2576504535ed
|
3 |
+
size 1114494339
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"model_max_length": 512}
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "name_or_path": "xlm-roberta-base"}
|