add tokenizer

vocab.json

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