add tokenizer

vocab.json

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