FarisHijazi's picture
add tokenizer
43f83a5
raw history blame
No virus
368 Bytes
{"â": 0, "ö": 1, "'": 2, "a": 3, "d": 4, "c": 5, "f": 6, "e": 7, "m": 8, "h": 9, "s": 10, "l": 11, "t": 12, "z": 13, "ş": 14, "ç": 15, "r": 16, "w": 17, "y": 18, "ğ": 20, "p": 21, "̇": 22, "ü": 23, "u": 24, "î": 25, "n": 26, "j": 27, "g": 28, "k": 29, "b": 30, "ë": 31, "o": 32, "ı": 33, "i": 34, "v": 35, "q": 36, "x": 37, "|": 19, "[UNK]": 38, "[PAD]": 39}