add tokenizer

vocab.json

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