nbaden's picture
Upload tokenizer
2cdb58c verified
raw
history blame contribute delete
558 Bytes
{
"[PAD]": 46,
"[UNK]": 45,
"c": 1,
"i": 2,
"o": 3,
"y": 4,
"|": 0,
"ç": 5,
"а": 6,
"б": 7,
"в": 8,
"г": 9,
"д": 10,
"е": 11,
"ж": 12,
"з": 13,
"и": 14,
"й": 15,
"к": 16,
"л": 17,
"м": 18,
"н": 19,
"о": 20,
"п": 21,
"р": 22,
"с": 23,
"т": 24,
"у": 25,
"ф": 26,
"х": 27,
"ц": 28,
"ч": 29,
"ш": 30,
"щ": 31,
"ъ": 32,
"ы": 33,
"ь": 34,
"э": 35,
"ю": 36,
"я": 37,
"і": 38,
"ј": 39,
"ҕ": 40,
"ҥ": 41,
"ү": 42,
"һ": 43,
"ө": 44
}