Samuael's picture
Upload tokenizer
125148c verified
raw
history blame
No virus
3.16 kB
{
"[PAD]": 0,
"[UNK]": 1,
"|": 2,
"ሁ": 39,
"ሂ": 40,
"ሄ": 41,
"ህ": 3,
"ሆ": 42,
"ለ": 43,
"ሉ": 44,
"ሊ": 45,
"ላ": 46,
"ሌ": 47,
"ል": 4,
"ሎ": 48,
"ሏ": 201,
"ሐ": 38,
"ሗ": 200,
"መ": 49,
"ሙ": 50,
"ሚ": 51,
"ማ": 52,
"ሜ": 53,
"ም": 5,
"ሞ": 54,
"ሟ": 202,
"ረ": 55,
"ሩ": 56,
"ሪ": 57,
"ራ": 58,
"ሬ": 59,
"ር": 6,
"ሮ": 60,
"ሯ": 203,
"ሰ": 61,
"ሱ": 62,
"ሲ": 63,
"ሳ": 64,
"ሴ": 65,
"ስ": 7,
"ሶ": 66,
"ሷ": 204,
"ሸ": 67,
"ሹ": 68,
"ሺ": 69,
"ሻ": 70,
"ሼ": 71,
"ሽ": 8,
"ሾ": 72,
"ሿ": 205,
"ቀ": 73,
"ቁ": 74,
"ቂ": 75,
"ቃ": 76,
"ቄ": 77,
"ቅ": 9,
"ቆ": 78,
"ቊ": 232,
"ቋ": 206,
"ቌ": 228,
"በ": 79,
"ቡ": 80,
"ቢ": 81,
"ባ": 82,
"ቤ": 83,
"ብ": 10,
"ቦ": 84,
"ቧ": 207,
"ቨ": 85,
"ቩ": 86,
"ቪ": 87,
"ቫ": 88,
"ቬ": 89,
"ቭ": 11,
"ቮ": 90,
"ቯ": 208,
"ተ": 91,
"ቱ": 92,
"ቲ": 93,
"ታ": 94,
"ቴ": 95,
"ት": 12,
"ቶ": 96,
"ቷ": 209,
"ቸ": 97,
"ቹ": 98,
"ቺ": 99,
"ቻ": 100,
"ቼ": 101,
"ች": 13,
"ቾ": 102,
"ቿ": 210,
"ኊ": 231,
"ኌ": 227,
"ነ": 103,
"ኑ": 104,
"ኒ": 105,
"ና": 106,
"ኔ": 107,
"ን": 14,
"ኖ": 108,
"ኗ": 211,
"ኘ": 109,
"ኙ": 110,
"ኚ": 111,
"ኛ": 112,
"ኜ": 113,
"ኝ": 15,
"ኞ": 114,
"ኟ": 212,
"አ": 31,
"ኡ": 32,
"ኢ": 33,
"ኤ": 34,
"እ": 35,
"ኦ": 36,
"ኧ": 30,
"ከ": 115,
"ኩ": 116,
"ኪ": 117,
"ካ": 118,
"ኬ": 119,
"ክ": 16,
"ኮ": 120,
"ኰ": 121,
"ኲ": 230,
"ኳ": 213,
"ኴ": 226,
"ኸ": 37,
"ወ": 122,
"ዉ": 123,
"ዊ": 124,
"ዋ": 125,
"ዌ": 126,
"ው": 17,
"ዎ": 127,
"ዘ": 128,
"ዙ": 129,
"ዚ": 130,
"ዛ": 131,
"ዜ": 132,
"ዝ": 18,
"ዞ": 133,
"ዟ": 214,
"ዠ": 134,
"ዡ": 135,
"ዢ": 136,
"ዣ": 137,
"ዤ": 138,
"ዥ": 19,
"ዦ": 139,
"ዧ": 215,
"የ": 140,
"ዩ": 141,
"ዪ": 142,
"ያ": 143,
"ዬ": 144,
"ይ": 20,
"ዮ": 145,
"ደ": 146,
"ዱ": 147,
"ዲ": 148,
"ዳ": 149,
"ዴ": 150,
"ድ": 21,
"ዶ": 151,
"ዷ": 216,
"ጀ": 152,
"ጁ": 153,
"ጂ": 154,
"ጃ": 155,
"ጄ": 156,
"ጅ": 22,
"ጆ": 157,
"ጇ": 217,
"ገ": 158,
"ጉ": 159,
"ጊ": 160,
"ጋ": 161,
"ጌ": 162,
"ግ": 23,
"ጐ": 163,
"ጒ": 229,
"ጓ": 218,
"ጔ": 225,
"ጠ": 164,
"ጡ": 165,
"ጢ": 166,
"ጣ": 167,
"ጤ": 168,
"ጥ": 24,
"ጦ": 169,
"ጧ": 219,
"ጨ": 170,
"ጩ": 171,
"ጪ": 172,
"ጫ": 173,
"ጬ": 174,
"ጭ": 25,
"ጮ": 175,
"ጯ": 220,
"ጰ": 176,
"ጱ": 177,
"ጲ": 178,
"ጳ": 179,
"ጴ": 180,
"ጵ": 26,
"ጶ": 181,
"ጷ": 221,
"ጸ": 182,
"ጹ": 183,
"ጺ": 184,
"ጻ": 185,
"ጼ": 186,
"ጽ": 27,
"ጾ": 187,
"ጿ": 222,
"ፈ": 188,
"ፉ": 189,
"ፊ": 190,
"ፋ": 191,
"ፌ": 192,
"ፍ": 28,
"ፎ": 193,
"ፏ": 223,
"ፐ": 194,
"ፑ": 195,
"ፒ": 196,
"ፓ": 197,
"ፔ": 198,
"ፕ": 29,
"ፖ": 199,
"ፗ": 224
}