Upload tokenizer

tokenizer_config.json

@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "2": {
+    "1": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "3": {
+    "2": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "5": {
+    "4": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -43,12 +43,15 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": false,
   "mask_token": "[MASK]",
+  "max_len": 512,
   "model_max_length": 512,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": null,
+  "strip_accents": false,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"