add tokenizer

vocab.json

@@ -1 +1 @@
-{"ж": 0, "н": 2, "б": 3, "у": 4, "т": 5, "ь": 6, "х": 7, "з": 8, "д": 9, "м": 10, "г": 11, "ч": 12, "и": 13, "п": 14, "к": 15, "ф": 16, "а": 17, "ц": 18, "ё": 19, "е": 20, "ы": 21, "ю": 22, "ш": 23, "в": 24, "щ": 25, "о": 26, "р": 27, "ъ": 28, "с": 29, "э": 30, "й": 31, "я": 32, "л": 33, "|": 1, "[UNK]": 34, "[PAD]": 35}
+{"б": 0, "ф": 2, "м": 3, "н": 4, "т": 5, "а": 6, "ю": 7, "г": 8, "у": 9, "э": 10, "к": 11, "ы": 12, "в": 13, "ь": 14, "я": 15, "ж": 16, "ё": 17, "ъ": 18, "х": 19, "щ": 20, "й": 21, "з": 22, "ш": 23, "п": 24, "ч": 25, "е": 26, "д": 27, "р": 28, "о": 29, "с": 30, "и": 31, "л": 32, "ц": 33, "|": 1, "[UNK]": 34, "[PAD]": 35}