diff --git a/src/transformers/models/fnet/modeling_fnet.py b/src/transformers/models/fnet/modeling_fnet.py
index f12281499b5a08..8ca717d119379a 100755
--- a/src/transformers/models/fnet/modeling_fnet.py
+++ b/src/transformers/models/fnet/modeling_fnet.py
@@ -17,7 +17,7 @@
 import warnings
 from dataclasses import dataclass
 from functools import partial
-from typing import Optional, Tuple
+from typing import Optional, Tuple, Union
 
 import torch
 import torch.utils.checkpoint
@@ -644,15 +644,15 @@ def set_output_embeddings(self, new_embeddings):
     @replace_return_docstrings(output_type=FNetForPreTrainingOutput, config_class=_CONFIG_FOR_DOC)
     def forward(
         self,
-        input_ids=None,
-        token_type_ids=None,
-        position_ids=None,
-        inputs_embeds=None,
-        labels=None,
-        next_sentence_label=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        next_sentence_label: Optional[torch.Tensor] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, FNetForPreTrainingOutput]:
         r"""
         labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
             Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
@@ -741,14 +741,14 @@ def set_output_embeddings(self, new_embeddings):
     )
     def forward(
         self,
-        input_ids=None,
-        token_type_ids=None,
-        position_ids=None,
-        inputs_embeds=None,
-        labels=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, MaskedLMOutput]:
         r"""
         labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
             Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
@@ -799,15 +799,15 @@ def __init__(self, config):
     @replace_return_docstrings(output_type=NextSentencePredictorOutput, config_class=_CONFIG_FOR_DOC)
     def forward(
         self,
-        input_ids=None,
-        token_type_ids=None,
-        position_ids=None,
-        inputs_embeds=None,
-        labels=None,
-        output_hidden_states=None,
-        return_dict=None,
+        input_ids: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
         **kwargs,
-    ):
+    ) -> Union[Tuple, NextSentencePredictorOutput]:
         r"""
         labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
             Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair
@@ -900,14 +900,14 @@ def __init__(self, config):
     )
     def forward(
         self,
-        input_ids=None,
-        token_type_ids=None,
-        position_ids=None,
-        inputs_embeds=None,
-        labels=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, SequenceClassifierOutput]:
         r"""
         labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
             Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
@@ -985,14 +985,14 @@ def __init__(self, config):
     )
     def forward(
         self,
-        input_ids=None,
-        token_type_ids=None,
-        position_ids=None,
-        inputs_embeds=None,
-        labels=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, MultipleChoiceModelOutput]:
         r"""
         labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
             Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
@@ -1067,14 +1067,14 @@ def __init__(self, config):
     )
     def forward(
         self,
-        input_ids=None,
-        token_type_ids=None,
-        position_ids=None,
-        inputs_embeds=None,
-        labels=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, TokenClassifierOutput]:
         r"""
         labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
             Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.
@@ -1136,15 +1136,15 @@ def __init__(self, config):
     )
     def forward(
         self,
-        input_ids=None,
-        token_type_ids=None,
-        position_ids=None,
-        inputs_embeds=None,
-        start_positions=None,
-        end_positions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        start_positions: Optional[torch.Tensor] = None,
+        end_positions: Optional[torch.Tensor] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, QuestionAnsweringModelOutput]:
         r"""
         start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
             Labels for position (index) of the start of the labelled span for computing the token classification loss.