Upload tokenizer

special_tokens_map.json

@@ -1,7 +1,9 @@
 {
   "bos_token": "<s>",
+  "cls_token": "<cls>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
   "pad_token": "<pad>",
+  "sep_token": "<sep>",
   "unk_token": "<unk>"
 }

tokenizer.json

@@ -47,6 +47,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 2894,
+      "content": "<sep>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2895,
+      "content": "<cls>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -39,15 +39,33 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "2894": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2895": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
+  "cls_token": "<cls>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "padding_side": "right",
+  "sep_token": "<sep>",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "truncation_side": "right",
   "unk_token": "<unk>"