add tokenizer

vocab.json

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