add tokenizer

added_tokens.json

@@ -1 +1 @@
-{"<s>": 48, "</s>": 49}
+{"<s>": 40, "</s>": 41}

vocab.json

@@ -1 +1 @@
-{"ء": 1, "آ": 2, "ؤ": 3, "ئ": 4, "ا": 5, "ب": 6, "ت": 7, "ث": 8, "ج": 9, "ح": 10, "خ": 11, "د": 12, "ذ": 13, "ر": 14, "ز": 15, "س": 16, "ش": 17, "ص": 18, "ض": 19, "ط": 20, "ظ": 21, "ع": 22, "غ": 23, "ف": 24, "ق": 25, "ل": 26, "م": 27, "ن": 28, "و": 29, "ى": 30, "ي": 31, "ٹ": 32, "پ": 33, "چ": 34, "ڈ": 35, "ڑ": 36, "ژ": 37, "ک": 38, "گ": 39, "ں": 40, "ھ": 41, "ہ": 42, "ۂ": 43, "ی": 44, "ے": 45, "|": 0, "[UNK]": 46, "[PAD]": 47}
+{"ا": 1, "ب": 2, "ت": 3, "ث": 4, "ج": 5, "ح": 6, "خ": 7, "د": 8, "ذ": 9, "ر": 10, "ز": 11, "س": 12, "ش": 13, "ص": 14, "ض": 15, "ط": 16, "ظ": 17, "ع": 18, "غ": 19, "ف": 20, "ق": 21, "ل": 22, "م": 23, "ن": 24, "و": 25, "ٹ": 26, "پ": 27, "چ": 28, "ڈ": 29, "ڑ": 30, "ژ": 31, "ک": 32, "گ": 33, "ھ": 34, "ہ": 35, "ی": 36, "ے": 37, "|": 0, "[UNK]": 38, "[PAD]": 39}