add tokenizer

vocab.json

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