Update modeling_norbert.py

modeling_norbert.py

@@ -329,6 +329,7 @@ class NorbertModel(NorbertPreTrainedModel):
         output_hidden_states: Optional[bool] = None,
         output_attentions: Optional[bool] = None,
         return_dict: Optional[bool] = None,
+        **kwargs
     ) -> Union[Tuple[torch.Tensor], BaseModelOutput]:
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
@@ -370,6 +371,7 @@ class NorbertForMaskedLM(NorbertModel):
         output_attentions: Optional[bool] = None,
         return_dict: Optional[bool] = None,
         labels: Optional[torch.LongTensor] = None,
+        **kwargs
     ) -> Union[Tuple[torch.Tensor], MaskedLMOutput]:
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
@@ -446,6 +448,7 @@ class NorbertForSequenceClassification(NorbertModel):
         output_hidden_states: Optional[bool] = None,
         return_dict: Optional[bool] = None,
         labels: Optional[torch.LongTensor] = None,
+        **kwargs
     ) -> Union[Tuple[torch.Tensor], SequenceClassifierOutput]:
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
@@ -511,6 +514,7 @@ class NorbertForTokenClassification(NorbertModel):
         output_hidden_states: Optional[bool] = None,
         return_dict: Optional[bool] = None,
         labels: Optional[torch.LongTensor] = None,
+        **kwargs
     ) -> Union[Tuple[torch.Tensor], TokenClassifierOutput]:
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
@@ -558,7 +562,8 @@ class NorbertForQuestionAnswering(NorbertModel):
         output_hidden_states: Optional[bool] = None,
         return_dict: Optional[bool] = None,
         start_positions: Optional[torch.Tensor] = None,
-        end_positions: Optional[torch.Tensor] = None
+        end_positions: Optional[torch.Tensor] = None,
+        **kwargs
     ) -> Union[Tuple[torch.Tensor], QuestionAnsweringModelOutput]:
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
@@ -624,7 +629,8 @@ class NorbertForMultipleChoice(NorbertModel):
         labels: Optional[torch.Tensor] = None,
         output_attentions: Optional[bool] = None,
         output_hidden_states: Optional[bool] = None,
-        return_dict: Optional[bool] = None
+        return_dict: Optional[bool] = None,
+        **kwargs
     ) -> Union[Tuple[torch.Tensor], MultipleChoiceModelOutput]:
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
         num_choices = input_ids.shape[1]