add tokenizer

vocab.json

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