add tokenizer

vocab.json

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