Upload tokenizer

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 34,
+  "<s>": 33,
+  "[PAD]": 32,
+  "[UNK]": 31
+}

tokenizer_config.json

@@ -1,4 +1,39 @@
 {
+  "added_tokens_decoder": {
+    "31": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": false,

vocab.json

@@ -1,37 +1,35 @@
 {
-  "[PAD]": 34,
-  "[UNK]": 33,
-  "|": 20,
-  "ء": 19,
+  "[PAD]": 32,
+  "[UNK]": 31,
+  "|": 18,
+  "ء": 12,
   "ا": 6,
-  "ب": 1,
-  "ة": 24,
-  "ت": 10,
-  "ث": 9,
-  "ج": 25,
-  "ح": 31,
-  "خ": 11,
-  "د": 29,
-  "ذ": 15,
-  "ر": 27,
-  "ز": 8,
-  "س": 21,
-  "ش": 5,
-  "ص": 3,
-  "ض": 14,
-  "ط": 16,
-  "ظ": 13,
-  "ع": 26,
-  "غ": 22,
-  "ـ": 12,
-  "ف": 23,
-  "ق": 32,
-  "ك": 7,
-  "ل": 18,
-  "م": 0,
-  "ن": 2,
-  "ه": 28,
-  "و": 30,
-  "ى": 4,
-  "ي": 17
+  "ب": 24,
+  "ة": 11,
+  "ت": 8,
+  "ث": 30,
+  "ج": 26,
+  "ح": 19,
+  "خ": 14,
+  "د": 28,
+  "ذ": 23,
+  "ر": 17,
+  "ز": 0,
+  "س": 10,
+  "ش": 25,
+  "ص": 21,
+  "ض": 1,
+  "ط": 2,
+  "ظ": 4,
+  "ع": 16,
+  "غ": 9,
+  "ف": 22,
+  "ق": 27,
+  "ك": 29,
+  "ل": 13,
+  "م": 20,
+  "ن": 5,
+  "ه": 3,
+  "و": 15,
+  "ي": 7
 }