add tokenizer

vocab.json

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