Upload tokenizer

tokenizer_config.json

@@ -43,11 +43,16 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_basic_tokenize": false,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
+  "never_split": [
+    "A",
+    "U",
+    "G",
+    "C"
+  ],
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,