Upload tokenizer

special_tokens_map.json

@@ -9,7 +9,7 @@
   "cls_token": {
     "content": "[CLS]",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
@@ -30,21 +30,21 @@
   "pad_token": {
     "content": "[PAD]",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
     "content": "[SEP]",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -23,7 +23,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -32,7 +32,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -41,7 +41,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -50,7 +50,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {

tokenizer_config.json

@@ -4,7 +4,7 @@
     "0": {
       "content": "[PAD]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -12,7 +12,7 @@
     "11": {
       "content": "[UNK]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,7 +20,7 @@
     "12": {
       "content": "[CLS]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -28,7 +28,7 @@
     "13": {
       "content": "[SEP]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -65,8 +65,8 @@
   "errors": "replace",
   "full_tokenizer_file": null,
   "mask_token": "[MASK]",
-  "max_len": 512,
-  "model_max_length": 512,
+  "max_len": 514,
+  "model_max_length": 514,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "tokenizer_class": "RobertaTokenizer",