add tokenizer

vocab.json

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