Upload tokenizer

added_tokens.json

@@ -18,6 +18,7 @@
   "6": 4019,
   "7": 4020,
   "8": 4021,
+  "9": 4022,
   ":": 4005,
   ";": 4006,
   "?": 4003

tokenizer.json

@@ -245,6 +245,15 @@
       "rstrip": false,
       "normalized": true,
       "special": false
+    },
+    {
+      "id": 4022,
+      "content": "9",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": false
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -1,13 +1,13 @@
 {
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }