add tokenizer

vocab.json

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