large_base_M07 / vocab.json
mprzibilla's picture
add tokenizer
f79bf57
raw
history blame
250 Bytes
{"g": 0, "j": 1, "y": 2, "t": 3, "p": 4, "h": 5, "a": 6, "s": 7, "q": 8, "v": 10, "n": 11, "c": 12, "o": 13, "w": 14, "e": 15, "k": 16, "m": 17, "l": 18, "i": 19, "f": 20, "d": 21, "b": 22, "u": 23, "r": 24, "x": 25, "|": 9, "[UNK]": 26, "[PAD]": 27}