add tokenizer

vocab.json

@@ -1 +1 @@
-{"l": 0, "H": 1, ".": 2, "t": 3, "G": 4, "L": 5, ";": 6, "a": 7, "C": 8, "n": 9, "R": 10, "N": 11, "-": 12, "Q": 13, "\"": 14, "w": 15, "q": 16, "X": 17, "P": 18, "'": 19, ":": 20, "M": 21, "F": 22, "r": 23, "j": 24, "z": 25, "B": 26, "v": 27, "W": 28, "D": 29, "s": 30, "c": 32, ",": 33, "f": 34, "O": 35, "u": 36, "?": 37, "E": 38, "b": 39, "A": 40, "T": 41, "k": 42, "K": 43, "d": 44, "Y": 45, "y": 46, "J": 47, "V": 48, "U": 49, "o": 50, "m": 51, "e": 52, "i": 53, "x": 54, "g": 55, "S": 56, "!": 57, "h": 58, "p": 59, "I": 60, "|": 31, "[UNK]": 61, "[PAD]": 62}
+{"u": 0, "g": 1, "Y": 2, ";": 3, "Q": 4, "S": 5, "?": 6, "k": 7, "!": 8, "h": 9, "m": 10, "P": 11, ":": 12, "H": 13, "a": 14, "o": 15, "J": 16, "A": 17, "U": 18, "W": 19, "G": 20, "w": 21, "e": 22, "\"": 23, "X": 24, "I": 25, "R": 26, "r": 27, "D": 28, "N": 29, "s": 30, "l": 31, "q": 32, "C": 33, "n": 34, "b": 35, "z": 36, "V": 37, "f": 38, ",": 39, "p": 40, "-": 41, "c": 42, "K": 43, "x": 44, "B": 45, "d": 46, "M": 47, "y": 49, "O": 50, "L": 51, "'": 52, "T": 53, "v": 54, ".": 55, "j": 56, "F": 57, "t": 58, "i": 59, "E": 60, "|": 48, "[UNK]": 61, "[PAD]": 62}