Update tokenizer_config.json

tokenizer_config.json

@@ -1050,8 +1050,21 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "model_max_length": 512,
+  "max_length": 1024,
+  "model_max_length": 1024,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "tokenizer_class": "T5Tokenizer",
-  "unk_token": "<unk>"
-}
+  "unk_token": "<unk>",
+  "enable_token_classification": true,
+  "normalization_rules": {
+    "enable": true,
+    "lowercase": true,
+    "strip_accents": true,
+    "pre_tokenization": {
+      "punctuation_split": true,
+      "split_digits": true
+    }
+  }
+}