add tokenizer

vocab.json

@@ -1 +1 @@
-{"e": 0, "t": 1, "q": 2, "d": 3, "w": 4, "l": 5, "x": 6, "k": 7, "m": 8, "o": 9, "s": 11, "f": 12, "z": 13, "b": 14, "p": 15, "n": 16, "i": 17, "y": 18, "j": 20, "v": 21, "a": 22, "c": 23, "g": 24, "u": 25, "h": 26, "r": 27, "[UNK]": 28, "[PAD]": 29, "|": 10}
+{"i": 0, "b": 1, "e": 2, "a": 3, "m": 4, "t": 5, "h": 6, "o": 9, "x": 10, "d": 11, "p": 12, "u": 13, "z": 14, "g": 15, "w": 16, "j": 17, "l": 18, "q": 19, "f": 20, "y": 21, "v": 22, "s": 23, "r": 24, "c": 25, "k": 26, "n": 27, "[UNK]": 28, "[PAD]": 29, "|": 8}