add tokenizer

vocab.json

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