diff --git a/src/transformers/models/bamba/modeling_bamba.py b/src/transformers/models/bamba/modeling_bamba.py
index c89d8d7853008d..ce39640e47f579 100644
--- a/src/transformers/models/bamba/modeling_bamba.py
+++ b/src/transformers/models/bamba/modeling_bamba.py
@@ -1204,6 +1204,7 @@ def forward(
         output_hidden_states: Optional[bool] = None,
         return_dict: Optional[bool] = None,
         cache_position: Optional[torch.LongTensor] = None,
+        **kwargs,
     ) -> Union[Tuple, BaseModelOutputWithPast]:
         output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
         output_hidden_states = (
diff --git a/src/transformers/models/bamba/modular_bamba.py b/src/transformers/models/bamba/modular_bamba.py
index 7fb35f48fb3b76..41a5034c7e6355 100644
--- a/src/transformers/models/bamba/modular_bamba.py
+++ b/src/transformers/models/bamba/modular_bamba.py
@@ -947,6 +947,7 @@ def forward(
         output_hidden_states: Optional[bool] = None,
         return_dict: Optional[bool] = None,
         cache_position: Optional[torch.LongTensor] = None,
+        **kwargs,
     ) -> Union[Tuple, BaseModelOutputWithPast]:
         output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
         output_hidden_states = (