Upload tokenizer
Browse files- added_tokens.json +7 -0
- merges.txt +305 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +56 -0
- vocab.json +306 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 305,
|
| 3 |
+
"<PAD>": 307,
|
| 4 |
+
"<mask>": 308,
|
| 5 |
+
"<s>": 304,
|
| 6 |
+
"<unk>": 306
|
| 7 |
+
}
|
merges.txt
ADDED
|
@@ -0,0 +1,305 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#version: 0.2
|
| 2 |
+
"<pad>": 0,
|
| 3 |
+
" ": 1,
|
| 4 |
+
"<BOS>": 2,
|
| 5 |
+
"<EOS>": 3,
|
| 6 |
+
"\u1200": 4,
|
| 7 |
+
"\u1201": 5,
|
| 8 |
+
"\u1202": 6,
|
| 9 |
+
"\u1203": 7,
|
| 10 |
+
"\u1204": 8,
|
| 11 |
+
"\u1205": 9,
|
| 12 |
+
"\u1206": 10,
|
| 13 |
+
"\u1208": 11,
|
| 14 |
+
"\u1209": 12,
|
| 15 |
+
"\u120a": 13,
|
| 16 |
+
"\u120b": 14,
|
| 17 |
+
"\u120c": 15,
|
| 18 |
+
"\u120d": 16,
|
| 19 |
+
"\u120e": 17,
|
| 20 |
+
"\u120f": 18,
|
| 21 |
+
"\u1210": 19,
|
| 22 |
+
"\u1211": 20,
|
| 23 |
+
"\u1212": 21,
|
| 24 |
+
"\u1213": 22,
|
| 25 |
+
"\u1214": 23,
|
| 26 |
+
"\u1215": 24,
|
| 27 |
+
"\u1216": 25,
|
| 28 |
+
"\u1218": 26,
|
| 29 |
+
"\u1219": 27,
|
| 30 |
+
"\u121a": 28,
|
| 31 |
+
"\u121b": 29,
|
| 32 |
+
"\u121c": 30,
|
| 33 |
+
"\u121d": 31,
|
| 34 |
+
"\u121e": 32,
|
| 35 |
+
"\u121f": 33,
|
| 36 |
+
"\u1220": 34,
|
| 37 |
+
"\u1221": 35,
|
| 38 |
+
"\u1222": 36,
|
| 39 |
+
"\u1223": 37,
|
| 40 |
+
"\u1224": 38,
|
| 41 |
+
"\u1225": 39,
|
| 42 |
+
"\u1226": 40,
|
| 43 |
+
"\u1227": 41,
|
| 44 |
+
"\u1228": 42,
|
| 45 |
+
"\u1229": 43,
|
| 46 |
+
"\u122a": 44,
|
| 47 |
+
"\u122b": 45,
|
| 48 |
+
"\u122c": 46,
|
| 49 |
+
"\u122d": 47,
|
| 50 |
+
"\u122e": 48,
|
| 51 |
+
"\u122f": 49,
|
| 52 |
+
"\u1230": 50,
|
| 53 |
+
"\u1231": 51,
|
| 54 |
+
"\u1232": 52,
|
| 55 |
+
"\u1233": 53,
|
| 56 |
+
"\u1234": 54,
|
| 57 |
+
"\u1235": 55,
|
| 58 |
+
"\u1236": 56,
|
| 59 |
+
"\u1237": 57,
|
| 60 |
+
"\u1238": 58,
|
| 61 |
+
"\u1239": 59,
|
| 62 |
+
"\u123a": 60,
|
| 63 |
+
"\u123b": 61,
|
| 64 |
+
"\u123c": 62,
|
| 65 |
+
"\u123d": 63,
|
| 66 |
+
"\u123e": 64,
|
| 67 |
+
"\u123f": 65,
|
| 68 |
+
"\u1240": 66,
|
| 69 |
+
"\u1241": 67,
|
| 70 |
+
"\u1242": 68,
|
| 71 |
+
"\u1243": 69,
|
| 72 |
+
"\u1244": 70,
|
| 73 |
+
"\u1245": 71,
|
| 74 |
+
"\u1246": 72,
|
| 75 |
+
"\u124b": 73,
|
| 76 |
+
"\u1260": 74,
|
| 77 |
+
"\u1261": 75,
|
| 78 |
+
"\u1262": 76,
|
| 79 |
+
"\u1263": 77,
|
| 80 |
+
"\u1264": 78,
|
| 81 |
+
"\u1265": 79,
|
| 82 |
+
"\u1266": 80,
|
| 83 |
+
"\u1267": 81,
|
| 84 |
+
"\u1268": 82,
|
| 85 |
+
"\u1269": 83,
|
| 86 |
+
"\u126a": 84,
|
| 87 |
+
"\u126b": 85,
|
| 88 |
+
"\u126c": 86,
|
| 89 |
+
"\u126d": 87,
|
| 90 |
+
"\u126e": 88,
|
| 91 |
+
"\u126f": 89,
|
| 92 |
+
"\u1270": 90,
|
| 93 |
+
"\u1271": 91,
|
| 94 |
+
"\u1272": 92,
|
| 95 |
+
"\u1273": 93,
|
| 96 |
+
"\u1274": 94,
|
| 97 |
+
"\u1275": 95,
|
| 98 |
+
"\u1276": 96,
|
| 99 |
+
"\u1277": 97,
|
| 100 |
+
"\u1278": 98,
|
| 101 |
+
"\u1279": 99,
|
| 102 |
+
"\u127a": 100,
|
| 103 |
+
"\u127b": 101,
|
| 104 |
+
"\u127c": 102,
|
| 105 |
+
"\u127d": 103,
|
| 106 |
+
"\u127e": 104,
|
| 107 |
+
"\u127f": 105,
|
| 108 |
+
"\u1280": 106,
|
| 109 |
+
"\u1281": 107,
|
| 110 |
+
"\u1282": 108,
|
| 111 |
+
"\u1283": 109,
|
| 112 |
+
"\u1284": 110,
|
| 113 |
+
"\u1285": 111,
|
| 114 |
+
"\u128b": 112,
|
| 115 |
+
"\u1290": 113,
|
| 116 |
+
"\u1291": 114,
|
| 117 |
+
"\u1292": 115,
|
| 118 |
+
"\u1293": 116,
|
| 119 |
+
"\u1294": 117,
|
| 120 |
+
"\u1295": 118,
|
| 121 |
+
"\u1296": 119,
|
| 122 |
+
"\u1297": 120,
|
| 123 |
+
"\u1298": 121,
|
| 124 |
+
"\u1299": 122,
|
| 125 |
+
"\u129a": 123,
|
| 126 |
+
"\u129b": 124,
|
| 127 |
+
"\u129c": 125,
|
| 128 |
+
"\u129d": 126,
|
| 129 |
+
"\u129e": 127,
|
| 130 |
+
"\u129f": 128,
|
| 131 |
+
"\u12a0": 129,
|
| 132 |
+
"\u12a1": 130,
|
| 133 |
+
"\u12a2": 131,
|
| 134 |
+
"\u12a3": 132,
|
| 135 |
+
"\u12a4": 133,
|
| 136 |
+
"\u12a5": 134,
|
| 137 |
+
"\u12a6": 135,
|
| 138 |
+
"\u12a7": 136,
|
| 139 |
+
"\u12a8": 137,
|
| 140 |
+
"\u12a9": 138,
|
| 141 |
+
"\u12aa": 139,
|
| 142 |
+
"\u12ab": 140,
|
| 143 |
+
"\u12ac": 141,
|
| 144 |
+
"\u12ad": 142,
|
| 145 |
+
"\u12ae": 143,
|
| 146 |
+
"\u12b3": 144,
|
| 147 |
+
"\u12b8": 145,
|
| 148 |
+
"\u12b9": 146,
|
| 149 |
+
"\u12ba": 147,
|
| 150 |
+
"\u12bb": 148,
|
| 151 |
+
"\u12bc": 149,
|
| 152 |
+
"\u12bd": 150,
|
| 153 |
+
"\u12be": 151,
|
| 154 |
+
"\u12c0": 152,
|
| 155 |
+
"\u12c3": 153,
|
| 156 |
+
"\u12c8": 154,
|
| 157 |
+
"\u12c9": 155,
|
| 158 |
+
"\u12ca": 156,
|
| 159 |
+
"\u12cb": 157,
|
| 160 |
+
"\u12cc": 158,
|
| 161 |
+
"\u12cd": 159,
|
| 162 |
+
"\u12ce": 160,
|
| 163 |
+
"\u12cf": 161,
|
| 164 |
+
"\u12d0": 162,
|
| 165 |
+
"\u12d1": 163,
|
| 166 |
+
"\u12d2": 164,
|
| 167 |
+
"\u12d3": 165,
|
| 168 |
+
"\u12d4": 166,
|
| 169 |
+
"\u12d5": 167,
|
| 170 |
+
"\u12d6": 168,
|
| 171 |
+
"\u12d8": 169,
|
| 172 |
+
"\u12d9": 170,
|
| 173 |
+
"\u12da": 171,
|
| 174 |
+
"\u12db": 172,
|
| 175 |
+
"\u12dc": 173,
|
| 176 |
+
"\u12dd": 174,
|
| 177 |
+
"\u12de": 175,
|
| 178 |
+
"\u12df": 176,
|
| 179 |
+
"\u12e0": 177,
|
| 180 |
+
"\u12e1": 178,
|
| 181 |
+
"\u12e2": 179,
|
| 182 |
+
"\u12e3": 180,
|
| 183 |
+
"\u12e4": 181,
|
| 184 |
+
"\u12e5": 182,
|
| 185 |
+
"\u12e6": 183,
|
| 186 |
+
"\u12e7": 184,
|
| 187 |
+
"\u12e8": 185,
|
| 188 |
+
"\u12e9": 186,
|
| 189 |
+
"\u12ea": 187,
|
| 190 |
+
"\u12eb": 188,
|
| 191 |
+
"\u12ec": 189,
|
| 192 |
+
"\u12ed": 190,
|
| 193 |
+
"\u12ee": 191,
|
| 194 |
+
"\u12f0": 192,
|
| 195 |
+
"\u12f1": 193,
|
| 196 |
+
"\u12f2": 194,
|
| 197 |
+
"\u12f3": 195,
|
| 198 |
+
"\u12f4": 196,
|
| 199 |
+
"\u12f5": 197,
|
| 200 |
+
"\u12f6": 198,
|
| 201 |
+
"\u12f7": 199,
|
| 202 |
+
"\u1300": 200,
|
| 203 |
+
"\u1301": 201,
|
| 204 |
+
"\u1302": 202,
|
| 205 |
+
"\u1303": 203,
|
| 206 |
+
"\u1304": 204,
|
| 207 |
+
"\u1305": 205,
|
| 208 |
+
"\u1306": 206,
|
| 209 |
+
"\u1307": 207,
|
| 210 |
+
"\u1308": 208,
|
| 211 |
+
"\u1309": 209,
|
| 212 |
+
"\u130a": 210,
|
| 213 |
+
"\u130b": 211,
|
| 214 |
+
"\u130c": 212,
|
| 215 |
+
"\u130d": 213,
|
| 216 |
+
"\u130e": 214,
|
| 217 |
+
"\u1313": 215,
|
| 218 |
+
"\u1320": 216,
|
| 219 |
+
"\u1321": 217,
|
| 220 |
+
"\u1322": 218,
|
| 221 |
+
"\u1323": 219,
|
| 222 |
+
"\u1324": 220,
|
| 223 |
+
"\u1325": 221,
|
| 224 |
+
"\u1326": 222,
|
| 225 |
+
"\u1327": 223,
|
| 226 |
+
"\u1328": 224,
|
| 227 |
+
"\u1329": 225,
|
| 228 |
+
"\u132a": 226,
|
| 229 |
+
"\u132b": 227,
|
| 230 |
+
"\u132c": 228,
|
| 231 |
+
"\u132d": 229,
|
| 232 |
+
"\u132e": 230,
|
| 233 |
+
"\u132f": 231,
|
| 234 |
+
"\u1330": 232,
|
| 235 |
+
"\u1331": 233,
|
| 236 |
+
"\u1332": 234,
|
| 237 |
+
"\u1333": 235,
|
| 238 |
+
"\u1334": 236,
|
| 239 |
+
"\u1335": 237,
|
| 240 |
+
"\u1336": 238,
|
| 241 |
+
"\u1337": 239,
|
| 242 |
+
"\u1338": 240,
|
| 243 |
+
"\u1339": 241,
|
| 244 |
+
"\u133a": 242,
|
| 245 |
+
"\u133b": 243,
|
| 246 |
+
"\u133c": 244,
|
| 247 |
+
"\u133d": 245,
|
| 248 |
+
"\u133e": 246,
|
| 249 |
+
"\u133f": 247,
|
| 250 |
+
"\u1340": 248,
|
| 251 |
+
"\u1341": 249,
|
| 252 |
+
"\u1342": 250,
|
| 253 |
+
"\u1343": 251,
|
| 254 |
+
"\u1344": 252,
|
| 255 |
+
"\u1345": 253,
|
| 256 |
+
"\u1346": 254,
|
| 257 |
+
"\u1347": 255,
|
| 258 |
+
"\u1348": 256,
|
| 259 |
+
"\u1349": 257,
|
| 260 |
+
"\u134a": 258,
|
| 261 |
+
"\u134b": 259,
|
| 262 |
+
"\u134c": 260,
|
| 263 |
+
"\u134d": 261,
|
| 264 |
+
"\u134e": 262,
|
| 265 |
+
"\u134f": 263,
|
| 266 |
+
"\u1350": 264,
|
| 267 |
+
"\u1351": 265,
|
| 268 |
+
"\u1352": 266,
|
| 269 |
+
"\u1353": 267,
|
| 270 |
+
"\u1354": 268,
|
| 271 |
+
"\u1355": 269,
|
| 272 |
+
"\u1356": 270,
|
| 273 |
+
"\u1357": 271,
|
| 274 |
+
"!": 272,
|
| 275 |
+
"\u1366": 273,
|
| 276 |
+
"\u2039": 274,
|
| 277 |
+
"(": 275,
|
| 278 |
+
"\u00ab": 276,
|
| 279 |
+
"\u1365": 277,
|
| 280 |
+
"%": 278,
|
| 281 |
+
"\u00bb": 279,
|
| 282 |
+
")": 280,
|
| 283 |
+
"\u203a": 281,
|
| 284 |
+
".": 282,
|
| 285 |
+
"+": 283,
|
| 286 |
+
"\u1363": 284,
|
| 287 |
+
"-": 285,
|
| 288 |
+
"\u1362": 286,
|
| 289 |
+
"/": 287,
|
| 290 |
+
"0": 288,
|
| 291 |
+
"1": 289,
|
| 292 |
+
"2": 290,
|
| 293 |
+
"3": 291,
|
| 294 |
+
"4": 292,
|
| 295 |
+
"5": 293,
|
| 296 |
+
"6": 294,
|
| 297 |
+
"7": 295,
|
| 298 |
+
"8": 296,
|
| 299 |
+
"9": 297,
|
| 300 |
+
"\u1361": 298,
|
| 301 |
+
"\u1364": 299,
|
| 302 |
+
"\u135d": 300,
|
| 303 |
+
"*": 301,
|
| 304 |
+
"#": 302,
|
| 305 |
+
"?": 303
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<PAD>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"304": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"305": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"306": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"307": {
|
| 29 |
+
"content": "<PAD>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"308": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<PAD>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,306 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
" ": 1,
|
| 3 |
+
"!": 272,
|
| 4 |
+
"#": 302,
|
| 5 |
+
"%": 278,
|
| 6 |
+
"(": 275,
|
| 7 |
+
")": 280,
|
| 8 |
+
"*": 301,
|
| 9 |
+
"+": 283,
|
| 10 |
+
"-": 285,
|
| 11 |
+
".": 282,
|
| 12 |
+
"/": 287,
|
| 13 |
+
"0": 288,
|
| 14 |
+
"1": 289,
|
| 15 |
+
"2": 290,
|
| 16 |
+
"3": 291,
|
| 17 |
+
"4": 292,
|
| 18 |
+
"5": 293,
|
| 19 |
+
"6": 294,
|
| 20 |
+
"7": 295,
|
| 21 |
+
"8": 296,
|
| 22 |
+
"9": 297,
|
| 23 |
+
"<BOS>": 2,
|
| 24 |
+
"<EOS>": 3,
|
| 25 |
+
"<pad>": 0,
|
| 26 |
+
"?": 303,
|
| 27 |
+
"«": 276,
|
| 28 |
+
"»": 279,
|
| 29 |
+
"ሀ": 4,
|
| 30 |
+
"ሁ": 5,
|
| 31 |
+
"ሂ": 6,
|
| 32 |
+
"ሃ": 7,
|
| 33 |
+
"ሄ": 8,
|
| 34 |
+
"ህ": 9,
|
| 35 |
+
"ሆ": 10,
|
| 36 |
+
"ለ": 11,
|
| 37 |
+
"ሉ": 12,
|
| 38 |
+
"ሊ": 13,
|
| 39 |
+
"ላ": 14,
|
| 40 |
+
"ሌ": 15,
|
| 41 |
+
"ል": 16,
|
| 42 |
+
"ሎ": 17,
|
| 43 |
+
"ሏ": 18,
|
| 44 |
+
"ሐ": 19,
|
| 45 |
+
"ሑ": 20,
|
| 46 |
+
"ሒ": 21,
|
| 47 |
+
"ሓ": 22,
|
| 48 |
+
"ሔ": 23,
|
| 49 |
+
"ሕ": 24,
|
| 50 |
+
"ሖ": 25,
|
| 51 |
+
"መ": 26,
|
| 52 |
+
"ሙ": 27,
|
| 53 |
+
"ሚ": 28,
|
| 54 |
+
"ማ": 29,
|
| 55 |
+
"ሜ": 30,
|
| 56 |
+
"ም": 31,
|
| 57 |
+
"ሞ": 32,
|
| 58 |
+
"ሟ": 33,
|
| 59 |
+
"ሠ": 34,
|
| 60 |
+
"ሡ": 35,
|
| 61 |
+
"ሢ": 36,
|
| 62 |
+
"ሣ": 37,
|
| 63 |
+
"ሤ": 38,
|
| 64 |
+
"ሥ": 39,
|
| 65 |
+
"ሦ": 40,
|
| 66 |
+
"ሧ": 41,
|
| 67 |
+
"ረ": 42,
|
| 68 |
+
"ሩ": 43,
|
| 69 |
+
"ሪ": 44,
|
| 70 |
+
"ራ": 45,
|
| 71 |
+
"ሬ": 46,
|
| 72 |
+
"ር": 47,
|
| 73 |
+
"ሮ": 48,
|
| 74 |
+
"ሯ": 49,
|
| 75 |
+
"ሰ": 50,
|
| 76 |
+
"ሱ": 51,
|
| 77 |
+
"ሲ": 52,
|
| 78 |
+
"ሳ": 53,
|
| 79 |
+
"ሴ": 54,
|
| 80 |
+
"ስ": 55,
|
| 81 |
+
"ሶ": 56,
|
| 82 |
+
"ሷ": 57,
|
| 83 |
+
"ሸ": 58,
|
| 84 |
+
"ሹ": 59,
|
| 85 |
+
"ሺ": 60,
|
| 86 |
+
"ሻ": 61,
|
| 87 |
+
"ሼ": 62,
|
| 88 |
+
"ሽ": 63,
|
| 89 |
+
"ሾ": 64,
|
| 90 |
+
"ሿ": 65,
|
| 91 |
+
"ቀ": 66,
|
| 92 |
+
"ቁ": 67,
|
| 93 |
+
"ቂ": 68,
|
| 94 |
+
"ቃ": 69,
|
| 95 |
+
"ቄ": 70,
|
| 96 |
+
"ቅ": 71,
|
| 97 |
+
"ቆ": 72,
|
| 98 |
+
"ቋ": 73,
|
| 99 |
+
"በ": 74,
|
| 100 |
+
"ቡ": 75,
|
| 101 |
+
"ቢ": 76,
|
| 102 |
+
"ባ": 77,
|
| 103 |
+
"ቤ": 78,
|
| 104 |
+
"ብ": 79,
|
| 105 |
+
"ቦ": 80,
|
| 106 |
+
"ቧ": 81,
|
| 107 |
+
"ቨ": 82,
|
| 108 |
+
"ቩ": 83,
|
| 109 |
+
"ቪ": 84,
|
| 110 |
+
"ቫ": 85,
|
| 111 |
+
"ቬ": 86,
|
| 112 |
+
"ቭ": 87,
|
| 113 |
+
"ቮ": 88,
|
| 114 |
+
"ቯ": 89,
|
| 115 |
+
"ተ": 90,
|
| 116 |
+
"ቱ": 91,
|
| 117 |
+
"ቲ": 92,
|
| 118 |
+
"ታ": 93,
|
| 119 |
+
"ቴ": 94,
|
| 120 |
+
"ት": 95,
|
| 121 |
+
"ቶ": 96,
|
| 122 |
+
"ቷ": 97,
|
| 123 |
+
"ቸ": 98,
|
| 124 |
+
"ቹ": 99,
|
| 125 |
+
"ቺ": 100,
|
| 126 |
+
"ቻ": 101,
|
| 127 |
+
"ቼ": 102,
|
| 128 |
+
"ች": 103,
|
| 129 |
+
"ቾ": 104,
|
| 130 |
+
"ቿ": 105,
|
| 131 |
+
"ኀ": 106,
|
| 132 |
+
"ኁ": 107,
|
| 133 |
+
"ኂ": 108,
|
| 134 |
+
"ኃ": 109,
|
| 135 |
+
"ኄ": 110,
|
| 136 |
+
"ኅ": 111,
|
| 137 |
+
"ኋ": 112,
|
| 138 |
+
"ነ": 113,
|
| 139 |
+
"ኑ": 114,
|
| 140 |
+
"ኒ": 115,
|
| 141 |
+
"ና": 116,
|
| 142 |
+
"ኔ": 117,
|
| 143 |
+
"ን": 118,
|
| 144 |
+
"ኖ": 119,
|
| 145 |
+
"ኗ": 120,
|
| 146 |
+
"ኘ": 121,
|
| 147 |
+
"ኙ": 122,
|
| 148 |
+
"ኚ": 123,
|
| 149 |
+
"ኛ": 124,
|
| 150 |
+
"ኜ": 125,
|
| 151 |
+
"ኝ": 126,
|
| 152 |
+
"ኞ": 127,
|
| 153 |
+
"ኟ": 128,
|
| 154 |
+
"አ": 129,
|
| 155 |
+
"ኡ": 130,
|
| 156 |
+
"ኢ": 131,
|
| 157 |
+
"ኣ": 132,
|
| 158 |
+
"ኤ": 133,
|
| 159 |
+
"እ": 134,
|
| 160 |
+
"ኦ": 135,
|
| 161 |
+
"ኧ": 136,
|
| 162 |
+
"ከ": 137,
|
| 163 |
+
"ኩ": 138,
|
| 164 |
+
"ኪ": 139,
|
| 165 |
+
"ካ": 140,
|
| 166 |
+
"ኬ": 141,
|
| 167 |
+
"ክ": 142,
|
| 168 |
+
"ኮ": 143,
|
| 169 |
+
"ኳ": 144,
|
| 170 |
+
"ኸ": 145,
|
| 171 |
+
"ኹ": 146,
|
| 172 |
+
"ኺ": 147,
|
| 173 |
+
"ኻ": 148,
|
| 174 |
+
"ኼ": 149,
|
| 175 |
+
"ኽ": 150,
|
| 176 |
+
"ኾ": 151,
|
| 177 |
+
"ዀ": 152,
|
| 178 |
+
"ዃ": 153,
|
| 179 |
+
"ወ": 154,
|
| 180 |
+
"ዉ": 155,
|
| 181 |
+
"ዊ": 156,
|
| 182 |
+
"ዋ": 157,
|
| 183 |
+
"ዌ": 158,
|
| 184 |
+
"ው": 159,
|
| 185 |
+
"ዎ": 160,
|
| 186 |
+
"ዏ": 161,
|
| 187 |
+
"ዐ": 162,
|
| 188 |
+
"ዑ": 163,
|
| 189 |
+
"ዒ": 164,
|
| 190 |
+
"ዓ": 165,
|
| 191 |
+
"ዔ": 166,
|
| 192 |
+
"ዕ": 167,
|
| 193 |
+
"ዖ": 168,
|
| 194 |
+
"ዘ": 169,
|
| 195 |
+
"ዙ": 170,
|
| 196 |
+
"ዚ": 171,
|
| 197 |
+
"ዛ": 172,
|
| 198 |
+
"ዜ": 173,
|
| 199 |
+
"ዝ": 174,
|
| 200 |
+
"ዞ": 175,
|
| 201 |
+
"ዟ": 176,
|
| 202 |
+
"ዠ": 177,
|
| 203 |
+
"ዡ": 178,
|
| 204 |
+
"ዢ": 179,
|
| 205 |
+
"ዣ": 180,
|
| 206 |
+
"ዤ": 181,
|
| 207 |
+
"ዥ": 182,
|
| 208 |
+
"ዦ": 183,
|
| 209 |
+
"ዧ": 184,
|
| 210 |
+
"የ": 185,
|
| 211 |
+
"ዩ": 186,
|
| 212 |
+
"ዪ": 187,
|
| 213 |
+
"ያ": 188,
|
| 214 |
+
"ዬ": 189,
|
| 215 |
+
"ይ": 190,
|
| 216 |
+
"ዮ": 191,
|
| 217 |
+
"ደ": 192,
|
| 218 |
+
"ዱ": 193,
|
| 219 |
+
"ዲ": 194,
|
| 220 |
+
"ዳ": 195,
|
| 221 |
+
"ዴ": 196,
|
| 222 |
+
"ድ": 197,
|
| 223 |
+
"ዶ": 198,
|
| 224 |
+
"ዷ": 199,
|
| 225 |
+
"ጀ": 200,
|
| 226 |
+
"ጁ": 201,
|
| 227 |
+
"ጂ": 202,
|
| 228 |
+
"ጃ": 203,
|
| 229 |
+
"ጄ": 204,
|
| 230 |
+
"ጅ": 205,
|
| 231 |
+
"ጆ": 206,
|
| 232 |
+
"ጇ": 207,
|
| 233 |
+
"ገ": 208,
|
| 234 |
+
"ጉ": 209,
|
| 235 |
+
"ጊ": 210,
|
| 236 |
+
"ጋ": 211,
|
| 237 |
+
"ጌ": 212,
|
| 238 |
+
"ግ": 213,
|
| 239 |
+
"ጎ": 214,
|
| 240 |
+
"ጓ": 215,
|
| 241 |
+
"ጠ": 216,
|
| 242 |
+
"ጡ": 217,
|
| 243 |
+
"ጢ": 218,
|
| 244 |
+
"ጣ": 219,
|
| 245 |
+
"ጤ": 220,
|
| 246 |
+
"ጥ": 221,
|
| 247 |
+
"ጦ": 222,
|
| 248 |
+
"ጧ": 223,
|
| 249 |
+
"ጨ": 224,
|
| 250 |
+
"ጩ": 225,
|
| 251 |
+
"ጪ": 226,
|
| 252 |
+
"ጫ": 227,
|
| 253 |
+
"ጬ": 228,
|
| 254 |
+
"ጭ": 229,
|
| 255 |
+
"ጮ": 230,
|
| 256 |
+
"ጯ": 231,
|
| 257 |
+
"ጰ": 232,
|
| 258 |
+
"ጱ": 233,
|
| 259 |
+
"ጲ": 234,
|
| 260 |
+
"ጳ": 235,
|
| 261 |
+
"ጴ": 236,
|
| 262 |
+
"ጵ": 237,
|
| 263 |
+
"ጶ": 238,
|
| 264 |
+
"ጷ": 239,
|
| 265 |
+
"ጸ": 240,
|
| 266 |
+
"ጹ": 241,
|
| 267 |
+
"ጺ": 242,
|
| 268 |
+
"ጻ": 243,
|
| 269 |
+
"ጼ": 244,
|
| 270 |
+
"ጽ": 245,
|
| 271 |
+
"ጾ": 246,
|
| 272 |
+
"ጿ": 247,
|
| 273 |
+
"ፀ": 248,
|
| 274 |
+
"ፁ": 249,
|
| 275 |
+
"ፂ": 250,
|
| 276 |
+
"ፃ": 251,
|
| 277 |
+
"ፄ": 252,
|
| 278 |
+
"ፅ": 253,
|
| 279 |
+
"ፆ": 254,
|
| 280 |
+
"ፇ": 255,
|
| 281 |
+
"ፈ": 256,
|
| 282 |
+
"ፉ": 257,
|
| 283 |
+
"ፊ": 258,
|
| 284 |
+
"ፋ": 259,
|
| 285 |
+
"ፌ": 260,
|
| 286 |
+
"ፍ": 261,
|
| 287 |
+
"ፎ": 262,
|
| 288 |
+
"ፏ": 263,
|
| 289 |
+
"ፐ": 264,
|
| 290 |
+
"ፑ": 265,
|
| 291 |
+
"ፒ": 266,
|
| 292 |
+
"ፓ": 267,
|
| 293 |
+
"ፔ": 268,
|
| 294 |
+
"ፕ": 269,
|
| 295 |
+
"ፖ": 270,
|
| 296 |
+
"ፗ": 271,
|
| 297 |
+
"፝": 300,
|
| 298 |
+
"፡": 298,
|
| 299 |
+
"።": 286,
|
| 300 |
+
"፣": 284,
|
| 301 |
+
"፤": 299,
|
| 302 |
+
"፥": 277,
|
| 303 |
+
"፦": 273,
|
| 304 |
+
"‹": 274,
|
| 305 |
+
"›": 281
|
| 306 |
+
}
|