special tokens without brackets

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fb0d6686f6933f72ed6dc1838b9a6084d735e50e9f8554615ddf5488a7c6624
+oid sha256:619fe89397d93fd0a9d08c5ac59c8a0f3235948849bad255c9f4a570f15860b7
 size 142920

special_tokens_map.json

@@ -1,9 +1,9 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": "CLS",
+  "cls_token": "CLS",
+  "eos_token": "SEP",
+  "mask_token": "MASK",
+  "pad_token": "PAD",
+  "sep_token": "SEP",
+  "unk_token": "UNK"
 }

tokenizer.json

@@ -5,7 +5,7 @@
   "added_tokens": [
     {
       "id": 0,
-      "content": "[UNK]",
+      "content": "UNK",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -14,7 +14,7 @@
     },
     {
       "id": 1,
-      "content": "[CLS]",
+      "content": "CLS",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -23,7 +23,7 @@
     },
     {
       "id": 2,
-      "content": "[SEP]",
+      "content": "SEP",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -32,7 +32,7 @@
     },
     {
       "id": 3,
-      "content": "[PAD]",
+      "content": "PAD",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -41,7 +41,7 @@
     },
     {
       "id": 4,
-      "content": "[MASK]",
+      "content": "MASK",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -80,7 +80,7 @@
     "single": [
       {
         "SpecialToken": {
-          "id": "[CLS]",
+          "id": "CLS",
           "type_id": 0
         }
       },
@@ -92,7 +92,7 @@
       },
       {
         "SpecialToken": {
-          "id": "[SEP]",
+          "id": "SEP",
           "type_id": 0
         }
       }
@@ -100,7 +100,7 @@
     "pair": [
       {
         "SpecialToken": {
-          "id": "[CLS]",
+          "id": "CLS",
           "type_id": 0
         }
       },
@@ -112,7 +112,7 @@
       },
       {
         "SpecialToken": {
-          "id": "[SEP]",
+          "id": "SEP",
           "type_id": 0
         }
       },
@@ -124,28 +124,28 @@
       },
       {
         "SpecialToken": {
-          "id": "[SEP]",
+          "id": "SEP",
           "type_id": 1
         }
       }
     ],
     "special_tokens": {
-      "[CLS]": {
-        "id": "[CLS]",
+      "CLS": {
+        "id": "CLS",
         "ids": [
           1
         ],
         "tokens": [
-          "[CLS]"
+          "CLS"
         ]
       },
-      "[SEP]": {
-        "id": "[SEP]",
+      "SEP": {
+        "id": "SEP",
         "ids": [
           2
         ],
         "tokens": [
-          "[SEP]"
+          "SEP"
         ]
       }
     }
@@ -154,11 +154,11 @@
   "model": {
     "type": "WordLevel",
     "vocab": {
-      "[UNK]": 0,
-      "[CLS]": 1,
-      "[SEP]": 2,
-      "[PAD]": 3,
-      "[MASK]": 4,
+      "UNK": 0,
+      "CLS": 1,
+      "SEP": 2,
+      "PAD": 3,
+      "MASK": 4,
       "boken": 5,
       "coken": 6,
       "doken": 7,
@@ -180,6 +180,6 @@
       "xoken": 23,
       "yoken": 24
     },
-    "unk_token": "[UNK]"
+    "unk_token": "UNK"
   }
 }

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[UNK]",
+      "content": "UNK",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": false
     },
     "1": {
-      "content": "[CLS]",
+      "content": "CLS",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": false
     },
     "2": {
-      "content": "[SEP]",
+      "content": "SEP",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -25,7 +25,7 @@
       "special": false
     },
     "3": {
-      "content": "[PAD]",
+      "content": "PAD",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -33,7 +33,7 @@
       "special": false
     },
     "4": {
-      "content": "[MASK]",
+      "content": "MASK",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -41,17 +41,17 @@
       "special": false
     }
   },
-  "bos_token": "[CLS]",
+  "bos_token": "CLS",
   "chat_template": "{% for message in messages %}{{ message['content'] }}{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
+  "cls_token": "CLS",
+  "eos_token": "SEP",
+  "mask_token": "MASK",
   "max_new_tokens": 1048576,
   "model_max_length": 1048576,
-  "pad_token": "[PAD]",
+  "pad_token": "PAD",
   "padding_side": "right",
-  "sep_token": "[SEP]",
+  "sep_token": "SEP",
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "[UNK]"
+  "unk_token": "UNK"
 }