Upload tokenizer

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,17 +1,16 @@
 {
-  "add_prefix_space": false,
-  "bos_token": "<s>",
-  "cls_token": "<s>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": false,
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "roberta-base",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
+  "name_or_path": "bert-base-cased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "special_tokens_map_file": null,
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }