Add type annotations for BERT and copies (#16074)

* Add type annotations for BERT and copies

* make fixup

src/transformers/models/bert/modeling_bert.py

@@ -20,7 +20,7 @@ import math
 import os
 import warnings
 from dataclasses import dataclass
-from typing import Optional, Tuple
+from typing import List, Optional, Tuple, Union
 
 import torch
 import torch.utils.checkpoint
@@ -893,20 +893,20 @@ class BertModel(BertPreTrainedModel):
     )
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        encoder_hidden_states=None,
-        encoder_attention_mask=None,
-        past_key_values=None,
-        use_cache=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: Optional[torch.Tensor] = None,
+        past_key_values: Optional[List[torch.FloatTensor]] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, BaseModelOutputWithPoolingAndCrossAttentions]:
         r"""
         encoder_hidden_states  (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
             Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
@@ -1048,18 +1048,18 @@ class BertForPreTraining(BertPreTrainedModel):
     @replace_return_docstrings(output_type=BertForPreTrainingOutput, config_class=_CONFIG_FOR_DOC)
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        labels=None,
-        next_sentence_label=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        next_sentence_label: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, BertForPreTrainingOutput]:
         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, ...,
@@ -1159,21 +1159,21 @@ class BertLMHeadModel(BertPreTrainedModel):
     @replace_return_docstrings(output_type=CausalLMOutputWithCrossAttentions, config_class=_CONFIG_FOR_DOC)
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        encoder_hidden_states=None,
-        encoder_attention_mask=None,
-        labels=None,
-        past_key_values=None,
-        use_cache=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        past_key_values: Optional[List[torch.Tensor]] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, CausalLMOutputWithCrossAttentions]:
         r"""
             encoder_hidden_states  (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
                 Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention
@@ -1318,19 +1318,19 @@ class BertForMaskedLM(BertPreTrainedModel):
     )
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        encoder_hidden_states=None,
-        encoder_attention_mask=None,
-        labels=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = 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, ...,
@@ -1408,18 +1408,18 @@ class BertForNextSentencePrediction(BertPreTrainedModel):
     @replace_return_docstrings(output_type=NextSentencePredictorOutput, config_class=_CONFIG_FOR_DOC)
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        labels=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = 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
@@ -1523,17 +1523,17 @@ class BertForSequenceClassification(BertPreTrainedModel):
     )
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        labels=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = 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, ...,
@@ -1623,17 +1623,17 @@ class BertForMultipleChoice(BertPreTrainedModel):
     )
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        labels=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = 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, ...,
@@ -1722,17 +1722,17 @@ class BertForTokenClassification(BertPreTrainedModel):
     )
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        labels=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = 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]`.
@@ -1803,18 +1803,18 @@ class BertForQuestionAnswering(BertPreTrainedModel):
     )
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        start_positions=None,
-        end_positions=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        start_positions: Optional[torch.Tensor] = None,
+        end_positions: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = 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.

src/transformers/models/data2vec/modeling_data2vec_text.py

@@ -15,6 +15,7 @@
 """PyTorch Data2VecText model."""
 
 import math
+from typing import List, Optional, Tuple, Union
 
 import torch
 import torch.utils.checkpoint
@@ -750,20 +751,20 @@ class Data2VecTextModel(Data2VecTextPreTrainedModel):
     # Copied from transformers.models.bert.modeling_bert.BertModel.forward
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        encoder_hidden_states=None,
-        encoder_attention_mask=None,
-        past_key_values=None,
-        use_cache=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: Optional[torch.Tensor] = None,
+        past_key_values: Optional[List[torch.FloatTensor]] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, BaseModelOutputWithPoolingAndCrossAttentions]:
         r"""
         encoder_hidden_states  (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
             Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if

src/transformers/models/mobilebert/modeling_mobilebert.py

@@ -24,7 +24,7 @@ import math
 import os
 import warnings
 from dataclasses import dataclass
-from typing import Optional, Tuple
+from typing import Optional, Tuple, Union
 
 import torch
 from torch import nn
@@ -1235,17 +1235,17 @@ class MobileBertForSequenceClassification(MobileBertPreTrainedModel):
     )
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        labels=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = 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, ...,
@@ -1336,18 +1336,18 @@ class MobileBertForQuestionAnswering(MobileBertPreTrainedModel):
     )
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        start_positions=None,
-        end_positions=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        start_positions: Optional[torch.Tensor] = None,
+        end_positions: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = 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.
@@ -1442,17 +1442,17 @@ class MobileBertForMultipleChoice(MobileBertPreTrainedModel):
     )
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        labels=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = 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, ...,
@@ -1542,17 +1542,17 @@ class MobileBertForTokenClassification(MobileBertPreTrainedModel):
     )
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        labels=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = 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]`.

src/transformers/models/roberta/modeling_roberta.py

@@ -16,6 +16,7 @@
 """PyTorch RoBERTa model."""
 
 import math
+from typing import List, Optional, Tuple, Union
 
 import torch
 import torch.utils.checkpoint
@@ -747,20 +748,20 @@ class RobertaModel(RobertaPreTrainedModel):
     # Copied from transformers.models.bert.modeling_bert.BertModel.forward
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        encoder_hidden_states=None,
-        encoder_attention_mask=None,
-        past_key_values=None,
-        use_cache=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: Optional[torch.Tensor] = None,
+        past_key_values: Optional[List[torch.FloatTensor]] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, BaseModelOutputWithPoolingAndCrossAttentions]:
         r"""
         encoder_hidden_states  (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
             Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if

src/transformers/models/xlm_roberta_xl/modeling_xlm_roberta_xl.py

@@ -15,6 +15,7 @@
 """PyTorch XLM RoBERTa xl,xxl model."""
 
 import math
+from typing import List, Optional, Tuple, Union
 
 import torch
 import torch.utils.checkpoint
@@ -718,20 +719,20 @@ class XLMRobertaXLModel(XLMRobertaXLPreTrainedModel):
     # Copied from transformers.models.bert.modeling_bert.BertModel.forward
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
-        inputs_embeds=None,
-        encoder_hidden_states=None,
-        encoder_attention_mask=None,
-        past_key_values=None,
-        use_cache=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: Optional[torch.Tensor] = None,
+        past_key_values: Optional[List[torch.FloatTensor]] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, BaseModelOutputWithPoolingAndCrossAttentions]:
         r"""
         encoder_hidden_states  (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
             Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if