Upload tokenizer

special_tokens_map.json

@@ -1,4 +1,6 @@
 {
+  "cls_token": "[CLS]",
   "mask_token": "[MASK]",
-  "pad_token": "PADDING_TOKEN"
+  "pad_token": "PADDING_TOKEN",
+  "sep_token": "[SEP]"
 }

tokenizer.json

@@ -14,6 +14,24 @@
     },
     {
       "id": 400006,
+      "content": "[CLS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 400007,
+      "content": "[SEP]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 400008,
       "content": "[MASK]",
       "single_word": false,
       "lstrip": false,
@@ -400036,7 +400054,9 @@
       "[unused0]": 400002,
       "[unused1]": 400003,
       "[Q]": 400004,
-      "[D]": 400005
+      "[D]": 400005,
+      "[CLS]": 400006,
+      "[SEP]": 400007
     },
     "unk_token": "[UNK]"
   }

tokenizer_config.json

@@ -9,6 +9,22 @@
       "special": true
     },
     "400006": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "400007": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "400008": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -18,8 +34,10 @@
     }
   },
   "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "PADDING_TOKEN",
+  "sep_token": "[SEP]",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }