add tokenizer

vocab.json

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