sanchit-gandhi's picture
Upload tokenizer
1e6cce9
raw
history blame
317 Bytes
{
" ": 28,
"-": 25,
"a": 2,
"b": 18,
"c": 4,
"d": 24,
"e": 6,
"h": 5,
"i": 1,
"j": 10,
"k": 11,
"l": 13,
"m": 17,
"n": 8,
"o": 9,
"p": 22,
"q": 21,
"r": 7,
"s": 20,
"t": 14,
"u": 12,
"w": 15,
"x": 19,
"y": 23,
"z": 26,
"|": 0,
"̱": 16,
"—": 27,
"ꞌ": 3
}