deepdml's picture
add tokenizer
e508b33
raw
history blame contribute delete
268 Bytes
{"j": 0, "x": 1, "t": 2, "u": 3, "a": 4, "n": 5, "s": 6, "d": 7, "p": 8, "k": 9, "c": 10, "i": 11, "e": 12, "g": 13, "h": 14, "l": 15, "'": 16, "q": 17, "m": 18, "v": 19, "b": 20, "f": 22, "r": 23, "z": 24, "o": 25, "w": 26, "y": 27, "|": 21, "[UNK]": 28, "[PAD]": 29}