add tokenizer

vocab.json

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