add tokenizer

vocab.json

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