add tokenizer

vocab.json

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