add tokenizer

vocab.json

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