simonlob_akylay_kaz / vocab.json
Simonlob's picture
Upload tokenizer
fbbbcec verified
raw
history blame
No virus
507 Bytes
{
" ": 38,
"-": 7,
"_": 13,
"а": 18,
"б": 3,
"в": 12,
"г": 32,
"д": 28,
"е": 25,
"ж": 26,
"з": 20,
"и": 36,
"й": 11,
"к": 14,
"л": 15,
"м": 19,
"н": 39,
"о": 37,
"п": 27,
"р": 0,
"с": 40,
"т": 1,
"у": 5,
"ф": 30,
"х": 21,
"ц": 17,
"ш": 10,
"щ": 24,
"ы": 9,
"ь": 6,
"э": 31,
"ю": 8,
"я": 41,
"і": 34,
"ғ": 35,
"қ": 33,
"ң": 16,
"ү": 4,
"ұ": 2,
"һ": 23,
"ә": 22,
"ө": 42,
"—": 29
}