add tokenizer

vocab.json

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