Update configuration_xlm_roberta.py

configuration_xlm_roberta.py

@@ -21,6 +21,7 @@ class XLMRobertaFlashConfig(PretrainedConfig):
             position_embedding_type="absolute",
             use_cache=True,
             classifier_dropout=None,
+            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)
@@ -39,4 +40,6 @@ class XLMRobertaFlashConfig(PretrainedConfig):
         self.layer_norm_eps = layer_norm_eps
         self.position_embedding_type = position_embedding_type
         self.use_cache = use_cache
-        self.classifier_dropout = classifier_dropout
+        self.classifier_dropout = classifier_dropout
+        self.use_flash_attn = use_flash_attn
+