add tokenizer

vocab.json

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