Update tokenizer_config.json

tokenizer_config.json

@@ -42,13 +42,14 @@
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "model_max_length": 512,
+  "model_max_length": 8192,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "sp_model_kwargs": {},
   "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }