add tokenizer

vocab.json

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