add tokenizer

vocab.json

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