Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 97,
-  "<s>": 96
+  "</s>": 90,
+  "<s>": 89
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "94": {
+    "87": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "95": {
+    "88": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "96": {
+    "89": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "97": {
+    "90": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,98 +1,91 @@
 {
   "(": 1,
   ")": 2,
-  "[PAD]": 95,
-  "[UNK]": 94,
-  "_": 3,
-  "a": 4,
-  "b": 5,
-  "c": 6,
-  "d": 7,
-  "e": 8,
-  "f": 9,
-  "g": 10,
-  "h": 11,
-  "i": 12,
-  "j": 13,
-  "k": 14,
-  "l": 15,
-  "m": 16,
-  "n": 17,
-  "o": 18,
-  "p": 19,
-  "q": 20,
-  "r": 21,
-  "s": 22,
-  "t": 23,
-  "u": 24,
-  "v": 25,
-  "w": 26,
-  "x": 27,
-  "y": 28,
+  "[PAD]": 88,
+  "[UNK]": 87,
+  "a": 3,
+  "b": 4,
+  "c": 5,
+  "d": 6,
+  "e": 7,
+  "g": 8,
+  "h": 9,
+  "i": 10,
+  "j": 11,
+  "k": 12,
+  "l": 13,
+  "m": 14,
+  "n": 15,
+  "o": 16,
+  "p": 17,
+  "q": 18,
+  "r": 19,
+  "s": 20,
+  "t": 21,
+  "u": 22,
+  "v": 23,
+  "x": 24,
+  "y": 25,
   "|": 0,
-  "«": 29,
-  "»": 30,
-  "،": 31,
-  "؛": 32,
-  "؟": 33,
-  "ء": 34,
-  "آ": 35,
-  "أ": 36,
-  "ؤ": 37,
-  "إ": 38,
-  "ئ": 39,
-  "ا": 40,
-  "ب": 41,
-  "ة": 42,
-  "ت": 43,
-  "ث": 44,
-  "ج": 45,
-  "ح": 46,
-  "خ": 47,
-  "د": 48,
-  "ذ": 49,
-  "ر": 50,
-  "ز": 51,
-  "س": 52,
-  "ش": 53,
-  "ص": 54,
-  "ض": 55,
-  "ط": 56,
-  "ظ": 57,
-  "ع": 58,
-  "غ": 59,
-  "ـ": 60,
-  "ف": 61,
-  "ق": 62,
-  "ك": 63,
-  "ل": 64,
-  "م": 65,
-  "ن": 66,
-  "ه": 67,
-  "و": 68,
-  "ى": 69,
-  "ي": 70,
-  "ً": 71,
-  "ٌ": 72,
-  "ٍ": 73,
-  "َ": 74,
-  "ُ": 75,
-  "ِ": 76,
-  "ّ": 77,
-  "ْ": 78,
-  "ٰ": 79,
-  "چ": 80,
-  "ڨ": 81,
-  "ک": 82,
-  "ھ": 83,
-  "ی": 84,
-  "ۖ": 85,
-  "ۗ": 86,
-  "ۘ": 87,
-  "ۚ": 88,
-  "ۛ": 89,
-  "—": 90,
-  "☭": 91,
-  "ﺃ": 92,
-  "ﻻ": 93
+  "«": 26,
+  "»": 27,
+  "،": 28,
+  "؛": 29,
+  "؟": 30,
+  "ء": 31,
+  "آ": 32,
+  "أ": 33,
+  "ؤ": 34,
+  "إ": 35,
+  "ئ": 36,
+  "ا": 37,
+  "ب": 38,
+  "ة": 39,
+  "ت": 40,
+  "ث": 41,
+  "ج": 42,
+  "ح": 43,
+  "خ": 44,
+  "د": 45,
+  "ذ": 46,
+  "ر": 47,
+  "ز": 48,
+  "س": 49,
+  "ش": 50,
+  "ص": 51,
+  "ض": 52,
+  "ط": 53,
+  "ظ": 54,
+  "ع": 55,
+  "غ": 56,
+  "ـ": 57,
+  "ف": 58,
+  "ق": 59,
+  "ك": 60,
+  "ل": 61,
+  "م": 62,
+  "ن": 63,
+  "ه": 64,
+  "و": 65,
+  "ى": 66,
+  "ي": 67,
+  "ً": 68,
+  "ٌ": 69,
+  "ٍ": 70,
+  "َ": 71,
+  "ُ": 72,
+  "ِ": 73,
+  "ّ": 74,
+  "ْ": 75,
+  "ٰ": 76,
+  "چ": 77,
+  "ک": 78,
+  "ھ": 79,
+  "ی": 80,
+  "ۖ": 81,
+  "ۗ": 82,
+  "ۚ": 83,
+  "—": 84,
+  "ﺃ": 85,
+  "ﻻ": 86
 }