add tokenizer

vocab.json

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