change tokenizer_class from PreTrainedTokenizerFast to BertTokenizerFast

special_tokens_map.json

@@ -1,12 +1,12 @@
 {
   "additional_special_tokens": [
-    "<EOD>"
+    "[EOD]"
   ],
   "bos_token": "<s>",
-  "cls_token": "<CLS>",
+  "cls_token": "[CLS]",
   "eos_token": "</s>",
-  "mask_token": "<MASK>",
-  "pad_token": "<PAD>",
-  "sep_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": "<PAD>",
+      "content": "[PAD]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -23,7 +23,7 @@
     },
     {
       "id": 2,
-      "content": "<CLS>",
+      "content": "[CLS]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -32,7 +32,7 @@
     },
     {
       "id": 3,
-      "content": "<SEP>",
+      "content": "[SEP]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -41,7 +41,7 @@
     },
     {
       "id": 4,
-      "content": "<MASK>",
+      "content": "[MASK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -50,7 +50,7 @@
     },
     {
       "id": 5,
-      "content": "<EOD>",
+      "content": "[EOD]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -86,7 +86,7 @@
     "single": [
       {
         "SpecialToken": {
-          "id": "<CLS>",
+          "id": "[CLS]",
           "type_id": 0
         }
       },
@@ -98,7 +98,7 @@
       },
       {
         "SpecialToken": {
-          "id": "<SEP>",
+          "id": "[SEP]",
           "type_id": 0
         }
       }
@@ -106,7 +106,7 @@
     "pair": [
       {
         "SpecialToken": {
-          "id": "<CLS>",
+          "id": "[CLS]",
           "type_id": 0
         }
       },
@@ -118,7 +118,7 @@
       },
       {
         "SpecialToken": {
-          "id": "<SEP>",
+          "id": "[SEP]",
           "type_id": 0
         }
       },
@@ -130,28 +130,28 @@
       },
       {
         "SpecialToken": {
-          "id": "<SEP>",
+          "id": "[SEP]",
           "type_id": 1
         }
       }
     ],
     "special_tokens": {
-      "<CLS>": {
-        "id": "<CLS>",
+      "[CLS]": {
+        "id": "[CLS]",
         "ids": [
           2
         ],
         "tokens": [
-          "<CLS>"
+          "[CLS]"
         ]
       },
-      "<SEP>": {
-        "id": "<SEP>",
+      "[SEP]": {
+        "id": "[SEP]",
         "ids": [
           3
         ],
         "tokens": [
-          "<SEP>"
+          "[SEP]"
         ]
       }
     }
@@ -172,7 +172,7 @@
     "unk_id": 0,
     "vocab": [
       [
-        "<PAD>",
+        "[PAD]",
         -1000.0
       ],
       [
@@ -180,19 +180,19 @@
         -1000.0
       ],
       [
-        "<CLS>",
+        "[CLS]",
         -1000.0
       ],
       [
-        "<SEP>",
+        "[SEP]",
         -1000.0
       ],
       [
-        "<MASK>",
+        "[MASK]",
         -1000.0
       ],
       [
-        "<EOD>",
+        "[EOD]",
         -1000.0
       ],
       [

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<PAD>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "<CLS>",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,7 +25,7 @@
       "special": true
     },
     "3": {
-      "content": "<SEP>",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -33,7 +33,7 @@
       "special": true
     },
     "4": {
-      "content": "<MASK>",
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,7 +41,7 @@
       "special": true
     },
     "5": {
-      "content": "<EOD>",
+      "content": "[EOD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -66,17 +66,20 @@
     }
   },
   "additional_special_tokens": [
-    "<EOD>"
+    "[EOD]"
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "<CLS>",
-  "eod_token": "<EOD>",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eod_token": "[EOD]",
   "eos_token": "</s>",
-  "mask_token": "<MASK>",
+  "mask_token": "[MASK]",
   "model_max_length": 2048,
-  "pad_token": "<PAD>",
-  "sep_token": "<SEP>",
-  "tokenizer_class": "PreTrainedTokenizerFast",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": false,
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "<unk>"
 }