add tokenizer

vocab.json

@@ -1 +1 @@
-{"q": 0, "p": 1, "r": 2, "i": 3, ".": 4, "m": 5, "l": 6, "e": 7, "h": 8, "v": 9, "w": 10, "o": 11, "y": 12, "'": 13, "n": 14, "j": 15, "d": 16, "u": 17, "c": 18, "t": 19, "s": 21, "z": 22, "k": 23, "x": 24, "a": 25, "f": 26, "b": 27, "g": 28, "|": 20, "[UNK]": 29, "[PAD]": 30}
+{"j": 0, ".": 1, "b": 2, "n": 3, "a": 4, "v": 5, "z": 6, "s": 7, "y": 8, "d": 9, "'": 10, "x": 11, "u": 12, "r": 13, "p": 14, "o": 15, "g": 16, "l": 17, "k": 18, "w": 20, "h": 21, "i": 22, "c": 23, "m": 24, "f": 25, "q": 26, "e": 27, "t": 28, "|": 19, "[UNK]": 29, "[PAD]": 30}