SheikhMiniMoE-Medical / tokenizer.json
OsamaBinLikhon's picture
Initial upload of SheikhMiniMoE medical model (2026-01-18)
268bce3 verified
{
"vocab_size": 5000,
"special_tokens": {
"<PAD>": 0,
"<UNK>": 1,
"<BOS>": 2,
"<EOS>": 3
},
"char_vocab": {
"\u0000": 4,
"\u0001": 5,
"\u0002": 6,
"\u0003": 7,
"\u0004": 8,
"\u0005": 9,
"\u0006": 10,
"\u0007": 11,
"\b": 12,
"\t": 13,
"\n": 14,
"\u000b": 15,
"\f": 16,
"\r": 17,
"\u000e": 18,
"\u000f": 19,
"\u0010": 20,
"\u0011": 21,
"\u0012": 22,
"\u0013": 23,
"\u0014": 24,
"\u0015": 25,
"\u0016": 26,
"\u0017": 27,
"\u0018": 28,
"\u0019": 29,
"\u001a": 30,
"\u001b": 31,
"\u001c": 32,
"\u001d": 33,
"\u001e": 34,
"\u001f": 35,
" ": 36,
"!": 37,
"\"": 38,
"#": 39,
"$": 40,
"%": 41,
"&": 42,
"'": 43,
"(": 44,
")": 45,
"*": 46,
"+": 47,
",": 48,
"-": 49,
".": 50,
"/": 51,
"0": 52,
"1": 53,
"2": 54,
"3": 55,
"4": 56,
"5": 57,
"6": 58,
"7": 59,
"8": 60,
"9": 61,
":": 62,
";": 63,
"<": 64,
"=": 65,
">": 66,
"?": 67,
"@": 68,
"A": 69,
"B": 70,
"C": 71,
"D": 72,
"E": 73,
"F": 74,
"G": 75,
"H": 76,
"I": 77,
"J": 78,
"K": 79,
"L": 80,
"M": 81,
"N": 82,
"O": 83,
"P": 84,
"Q": 85,
"R": 86,
"S": 87,
"T": 88,
"U": 89,
"V": 90,
"W": 91,
"X": 92,
"Y": 93,
"Z": 94,
"[": 95,
"\\": 96,
"]": 97,
"^": 98,
"_": 99,
"`": 100,
"a": 101,
"b": 102,
"c": 103,
"d": 104,
"e": 105,
"f": 106,
"g": 107,
"h": 108,
"i": 109,
"j": 110,
"k": 111,
"l": 112,
"m": 113,
"n": 114,
"o": 115,
"p": 116,
"q": 117,
"r": 118,
"s": 119,
"t": 120,
"u": 121,
"v": 122,
"w": 123,
"x": 124,
"y": 125,
"z": 126,
"{": 127,
"|": 128,
"}": 129,
"~": 130,
"\u007f": 131,
"\u0080": 132,
"\u0081": 133,
"\u0082": 134,
"\u0083": 135,
"\u0084": 136,
"\u0085": 137,
"\u0086": 138,
"\u0087": 139,
"\u0088": 140,
"\u0089": 141,
"\u008a": 142,
"\u008b": 143,
"\u008c": 144,
"\u008d": 145,
"\u008e": 146,
"\u008f": 147,
"\u0090": 148,
"\u0091": 149,
"\u0092": 150,
"\u0093": 151,
"\u0094": 152,
"\u0095": 153,
"\u0096": 154,
"\u0097": 155,
"\u0098": 156,
"\u0099": 157,
"\u009a": 158,
"\u009b": 159,
"\u009c": 160,
"\u009d": 161,
"\u009e": 162,
"\u009f": 163,
"\u00a0": 164,
"\u00a1": 165,
"\u00a2": 166,
"\u00a3": 167,
"\u00a4": 168,
"\u00a5": 169,
"\u00a6": 170,
"\u00a7": 171,
"\u00a8": 172,
"\u00a9": 173,
"\u00aa": 174,
"\u00ab": 175,
"\u00ac": 176,
"\u00ad": 177,
"\u00ae": 178,
"\u00af": 179,
"\u00b0": 180,
"\u00b1": 181,
"\u00b2": 182,
"\u00b3": 183,
"\u00b4": 184,
"\u00b5": 185,
"\u00b6": 186,
"\u00b7": 187,
"\u00b8": 188,
"\u00b9": 189,
"\u00ba": 190,
"\u00bb": 191,
"\u00bc": 192,
"\u00bd": 193,
"\u00be": 194,
"\u00bf": 195,
"\u00c0": 196,
"\u00c1": 197,
"\u00c2": 198,
"\u00c3": 199,
"\u00c4": 200,
"\u00c5": 201,
"\u00c6": 202,
"\u00c7": 203,
"\u00c8": 204,
"\u00c9": 205,
"\u00ca": 206,
"\u00cb": 207,
"\u00cc": 208,
"\u00cd": 209,
"\u00ce": 210,
"\u00cf": 211,
"\u00d0": 212,
"\u00d1": 213,
"\u00d2": 214,
"\u00d3": 215,
"\u00d4": 216,
"\u00d5": 217,
"\u00d6": 218,
"\u00d7": 219,
"\u00d8": 220,
"\u00d9": 221,
"\u00da": 222,
"\u00db": 223,
"\u00dc": 224,
"\u00dd": 225,
"\u00de": 226,
"\u00df": 227,
"\u00e0": 228,
"\u00e1": 229,
"\u00e2": 230,
"\u00e3": 231,
"\u00e4": 232,
"\u00e5": 233,
"\u00e6": 234,
"\u00e7": 235,
"\u00e8": 236,
"\u00e9": 237,
"\u00ea": 238,
"\u00eb": 239,
"\u00ec": 240,
"\u00ed": 241,
"\u00ee": 242,
"\u00ef": 243,
"\u00f0": 244,
"\u00f1": 245,
"\u00f2": 246,
"\u00f3": 247,
"\u00f4": 248,
"\u00f5": 249,
"\u00f6": 250,
"\u00f7": 251,
"\u00f8": 252,
"\u00f9": 253,
"\u00fa": 254,
"\u00fb": 255,
"\u00fc": 256,
"\u00fd": 257,
"\u00fe": 258,
"\u00ff": 259,
"\u0980": 256,
"\u0981": 257,
"\u0982": 258,
"\u0983": 259,
"\u0984": 260,
"\u0985": 261,
"\u0986": 262,
"\u0987": 263,
"\u0988": 264,
"\u0989": 265,
"\u098a": 266,
"\u098b": 267,
"\u098c": 268,
"\u098d": 269,
"\u098e": 270,
"\u098f": 271,
"\u0990": 272,
"\u0991": 273,
"\u0992": 274,
"\u0993": 275,
"\u0994": 276,
"\u0995": 277,
"\u0996": 278,
"\u0997": 279,
"\u0998": 280,
"\u0999": 281,
"\u099a": 282,
"\u099b": 283,
"\u099c": 284,
"\u099d": 285,
"\u099e": 286,
"\u099f": 287,
"\u09a0": 288,
"\u09a1": 289,
"\u09a2": 290,
"\u09a3": 291,
"\u09a4": 292,
"\u09a5": 293,
"\u09a6": 294,
"\u09a7": 295,
"\u09a8": 296,
"\u09a9": 297,
"\u09aa": 298,
"\u09ab": 299,
"\u09ac": 300,
"\u09ad": 301,
"\u09ae": 302,
"\u09af": 303,
"\u09b0": 304,
"\u09b1": 305,
"\u09b2": 306,
"\u09b3": 307,
"\u09b4": 308,
"\u09b5": 309,
"\u09b6": 310,
"\u09b7": 311,
"\u09b8": 312,
"\u09b9": 313,
"\u09ba": 314,
"\u09bb": 315,
"\u09bc": 316,
"\u09bd": 317,
"\u09be": 318,
"\u09bf": 319,
"\u09c0": 320,
"\u09c1": 321,
"\u09c2": 322,
"\u09c3": 323,
"\u09c4": 324,
"\u09c5": 325,
"\u09c6": 326,
"\u09c7": 327,
"\u09c8": 328,
"\u09c9": 329,
"\u09ca": 330,
"\u09cb": 331,
"\u09cc": 332,
"\u09cd": 333,
"\u09ce": 334,
"\u09cf": 335,
"\u09d0": 336,
"\u09d1": 337,
"\u09d2": 338,
"\u09d3": 339,
"\u09d4": 340,
"\u09d5": 341,
"\u09d6": 342,
"\u09d7": 343,
"\u09d8": 344,
"\u09d9": 345,
"\u09da": 346,
"\u09db": 347,
"\u09dc": 348,
"\u09dd": 349,
"\u09de": 350,
"\u09df": 351,
"\u09e0": 352,
"\u09e1": 353,
"\u09e2": 354,
"\u09e3": 355,
"\u09e4": 356,
"\u09e5": 357,
"\u09e6": 358,
"\u09e7": 359,
"\u09e8": 360,
"\u09e9": 361,
"\u09ea": 362,
"\u09eb": 363,
"\u09ec": 364,
"\u09ed": 365,
"\u09ee": 366,
"\u09ef": 367,
"\u09f0": 368,
"\u09f1": 369,
"\u09f2": 370,
"\u09f3": 371,
"\u09f4": 372,
"\u09f5": 373,
"\u09f6": 374,
"\u09f7": 375,
"\u09f8": 376,
"\u09f9": 377,
"\u09fa": 378,
"\u09fb": 379,
"\u09fc": 380,
"\u09fd": 381,
"\u09fe": 382
}
}