add tokenizer

vocab.json

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