add tokenizer

vocab.json

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