seq2seq-amharic / merges.txt
Samuael's picture
Upload tokenizer
ff1e6f5
#version: 0.2
"<pad>": 0,
" ": 1,
"<BOS>": 2,
"<EOS>": 3,
"\u1200": 4,
"\u1201": 5,
"\u1202": 6,
"\u1203": 7,
"\u1204": 8,
"\u1205": 9,
"\u1206": 10,
"\u1208": 11,
"\u1209": 12,
"\u120a": 13,
"\u120b": 14,
"\u120c": 15,
"\u120d": 16,
"\u120e": 17,
"\u120f": 18,
"\u1210": 19,
"\u1211": 20,
"\u1212": 21,
"\u1213": 22,
"\u1214": 23,
"\u1215": 24,
"\u1216": 25,
"\u1218": 26,
"\u1219": 27,
"\u121a": 28,
"\u121b": 29,
"\u121c": 30,
"\u121d": 31,
"\u121e": 32,
"\u121f": 33,
"\u1220": 34,
"\u1221": 35,
"\u1222": 36,
"\u1223": 37,
"\u1224": 38,
"\u1225": 39,
"\u1226": 40,
"\u1227": 41,
"\u1228": 42,
"\u1229": 43,
"\u122a": 44,
"\u122b": 45,
"\u122c": 46,
"\u122d": 47,
"\u122e": 48,
"\u122f": 49,
"\u1230": 50,
"\u1231": 51,
"\u1232": 52,
"\u1233": 53,
"\u1234": 54,
"\u1235": 55,
"\u1236": 56,
"\u1237": 57,
"\u1238": 58,
"\u1239": 59,
"\u123a": 60,
"\u123b": 61,
"\u123c": 62,
"\u123d": 63,
"\u123e": 64,
"\u123f": 65,
"\u1240": 66,
"\u1241": 67,
"\u1242": 68,
"\u1243": 69,
"\u1244": 70,
"\u1245": 71,
"\u1246": 72,
"\u124b": 73,
"\u1260": 74,
"\u1261": 75,
"\u1262": 76,
"\u1263": 77,
"\u1264": 78,
"\u1265": 79,
"\u1266": 80,
"\u1267": 81,
"\u1268": 82,
"\u1269": 83,
"\u126a": 84,
"\u126b": 85,
"\u126c": 86,
"\u126d": 87,
"\u126e": 88,
"\u126f": 89,
"\u1270": 90,
"\u1271": 91,
"\u1272": 92,
"\u1273": 93,
"\u1274": 94,
"\u1275": 95,
"\u1276": 96,
"\u1277": 97,
"\u1278": 98,
"\u1279": 99,
"\u127a": 100,
"\u127b": 101,
"\u127c": 102,
"\u127d": 103,
"\u127e": 104,
"\u127f": 105,
"\u1280": 106,
"\u1281": 107,
"\u1282": 108,
"\u1283": 109,
"\u1284": 110,
"\u1285": 111,
"\u128b": 112,
"\u1290": 113,
"\u1291": 114,
"\u1292": 115,
"\u1293": 116,
"\u1294": 117,
"\u1295": 118,
"\u1296": 119,
"\u1297": 120,
"\u1298": 121,
"\u1299": 122,
"\u129a": 123,
"\u129b": 124,
"\u129c": 125,
"\u129d": 126,
"\u129e": 127,
"\u129f": 128,
"\u12a0": 129,
"\u12a1": 130,
"\u12a2": 131,
"\u12a3": 132,
"\u12a4": 133,
"\u12a5": 134,
"\u12a6": 135,
"\u12a7": 136,
"\u12a8": 137,
"\u12a9": 138,
"\u12aa": 139,
"\u12ab": 140,
"\u12ac": 141,
"\u12ad": 142,
"\u12ae": 143,
"\u12b3": 144,
"\u12b8": 145,
"\u12b9": 146,
"\u12ba": 147,
"\u12bb": 148,
"\u12bc": 149,
"\u12bd": 150,
"\u12be": 151,
"\u12c0": 152,
"\u12c3": 153,
"\u12c8": 154,
"\u12c9": 155,
"\u12ca": 156,
"\u12cb": 157,
"\u12cc": 158,
"\u12cd": 159,
"\u12ce": 160,
"\u12cf": 161,
"\u12d0": 162,
"\u12d1": 163,
"\u12d2": 164,
"\u12d3": 165,
"\u12d4": 166,
"\u12d5": 167,
"\u12d6": 168,
"\u12d8": 169,
"\u12d9": 170,
"\u12da": 171,
"\u12db": 172,
"\u12dc": 173,
"\u12dd": 174,
"\u12de": 175,
"\u12df": 176,
"\u12e0": 177,
"\u12e1": 178,
"\u12e2": 179,
"\u12e3": 180,
"\u12e4": 181,
"\u12e5": 182,
"\u12e6": 183,
"\u12e7": 184,
"\u12e8": 185,
"\u12e9": 186,
"\u12ea": 187,
"\u12eb": 188,
"\u12ec": 189,
"\u12ed": 190,
"\u12ee": 191,
"\u12f0": 192,
"\u12f1": 193,
"\u12f2": 194,
"\u12f3": 195,
"\u12f4": 196,
"\u12f5": 197,
"\u12f6": 198,
"\u12f7": 199,
"\u1300": 200,
"\u1301": 201,
"\u1302": 202,
"\u1303": 203,
"\u1304": 204,
"\u1305": 205,
"\u1306": 206,
"\u1307": 207,
"\u1308": 208,
"\u1309": 209,
"\u130a": 210,
"\u130b": 211,
"\u130c": 212,
"\u130d": 213,
"\u130e": 214,
"\u1313": 215,
"\u1320": 216,
"\u1321": 217,
"\u1322": 218,
"\u1323": 219,
"\u1324": 220,
"\u1325": 221,
"\u1326": 222,
"\u1327": 223,
"\u1328": 224,
"\u1329": 225,
"\u132a": 226,
"\u132b": 227,
"\u132c": 228,
"\u132d": 229,
"\u132e": 230,
"\u132f": 231,
"\u1330": 232,
"\u1331": 233,
"\u1332": 234,
"\u1333": 235,
"\u1334": 236,
"\u1335": 237,
"\u1336": 238,
"\u1337": 239,
"\u1338": 240,
"\u1339": 241,
"\u133a": 242,
"\u133b": 243,
"\u133c": 244,
"\u133d": 245,
"\u133e": 246,
"\u133f": 247,
"\u1340": 248,
"\u1341": 249,
"\u1342": 250,
"\u1343": 251,
"\u1344": 252,
"\u1345": 253,
"\u1346": 254,
"\u1347": 255,
"\u1348": 256,
"\u1349": 257,
"\u134a": 258,
"\u134b": 259,
"\u134c": 260,
"\u134d": 261,
"\u134e": 262,
"\u134f": 263,
"\u1350": 264,
"\u1351": 265,
"\u1352": 266,
"\u1353": 267,
"\u1354": 268,
"\u1355": 269,
"\u1356": 270,
"\u1357": 271,
"!": 272,
"\u1366": 273,
"\u2039": 274,
"(": 275,
"\u00ab": 276,
"\u1365": 277,
"%": 278,
"\u00bb": 279,
")": 280,
"\u203a": 281,
".": 282,
"+": 283,
"\u1363": 284,
"-": 285,
"\u1362": 286,
"/": 287,
"0": 288,
"1": 289,
"2": 290,
"3": 291,
"4": 292,
"5": 293,
"6": 294,
"7": 295,
"8": 296,
"9": 297,
"\u1361": 298,
"\u1364": 299,
"\u135d": 300,
"*": 301,
"#": 302,
"?": 303