Update configuration_xlm_roberta.py

configuration_xlm_roberta.py

@@ -21,7 +21,7 @@ class XLMRobertaFlashConfig(PretrainedConfig):
             position_embedding_type="absolute",
             use_cache=True,
             classifier_dropout=None,
-            use_flash_attn=True
+            use_flash_attn=True,
             **kwargs,
     ):
         super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)