add tokenizer

vocab.json

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