Add type hints for ProphetNet PyTorch (#16272)

src/transformers/models/prophetnet/modeling_prophetnet.py

@@ -18,7 +18,7 @@ import copy
 import math
 import warnings
 from dataclasses import dataclass
-from typing import Optional, Tuple
+from typing import Optional, Tuple, Union
 
 import torch
 import torch.utils.checkpoint
@@ -1275,14 +1275,14 @@ class ProphetNetEncoder(ProphetNetPreTrainedModel):
     @replace_return_docstrings(output_type=BaseModelOutput, config_class=_CONFIG_FOR_DOC)
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        head_mask=None,
-        inputs_embeds=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, BaseModelOutput]:
         r"""
         Returns:
 
@@ -1422,19 +1422,19 @@ class ProphetNetDecoder(ProphetNetPreTrainedModel):
     @replace_return_docstrings(output_type=ProphetNetDecoderModelOutput, config_class=_CONFIG_FOR_DOC)
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        encoder_hidden_states=None,
-        encoder_attention_mask=None,
-        head_mask=None,
-        cross_attn_head_mask=None,
-        past_key_values=None,
-        inputs_embeds=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,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        cross_attn_head_mask: Optional[torch.Tensor] = None,
+        past_key_values: Optional[Tuple[Tuple[torch.Tensor]]] = None,
+        inputs_embeds: Optional[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, ProphetNetDecoderModelOutput]:
         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
@@ -1784,22 +1784,22 @@ class ProphetNetModel(ProphetNetPreTrainedModel):
     @replace_return_docstrings(output_type=ProphetNetSeq2SeqModelOutput, config_class=_CONFIG_FOR_DOC)
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        decoder_input_ids=None,
-        decoder_attention_mask=None,
-        head_mask=None,
-        decoder_head_mask=None,
-        cross_attn_head_mask=None,
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        decoder_input_ids: Optional[torch.Tensor] = None,
+        decoder_attention_mask: Optional[torch.BoolTensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        decoder_head_mask: Optional[torch.Tensor] = None,
+        cross_attn_head_mask: Optional[torch.Tensor] = None,
         encoder_outputs: Optional[Tuple] = None,
-        past_key_values=None,
-        inputs_embeds=None,
-        decoder_inputs_embeds=None,
-        use_cache=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-    ):
+        past_key_values: Optional[Tuple[Tuple[torch.Tensor]]] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        decoder_inputs_embeds: Optional[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, ProphetNetSeq2SeqModelOutput]:
         r"""
         Returns:
 
@@ -1900,23 +1900,23 @@ class ProphetNetForConditionalGeneration(ProphetNetPreTrainedModel):
     @replace_return_docstrings(output_type=ProphetNetSeq2SeqLMOutput, config_class=_CONFIG_FOR_DOC)
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        decoder_input_ids=None,
-        decoder_attention_mask=None,
-        head_mask=None,
-        decoder_head_mask=None,
-        cross_attn_head_mask=None,
-        encoder_outputs=None,
-        past_key_values=None,
-        inputs_embeds=None,
-        decoder_inputs_embeds=None,
-        labels=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,
+        decoder_input_ids: Optional[torch.Tensor] = None,
+        decoder_attention_mask: Optional[torch.BoolTensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        decoder_head_mask: Optional[torch.Tensor] = None,
+        cross_attn_head_mask: Optional[torch.Tensor] = None,
+        encoder_outputs: Optional[torch.Tensor] = None,
+        past_key_values: Optional[Tuple[Tuple[torch.Tensor]]] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        decoder_inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[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, ProphetNetSeq2SeqLMOutput]:
         r"""
         labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
             Labels for computing the sequence classification/regression loss. Indices should be in `[-100, 0, ...,
@@ -2123,20 +2123,20 @@ class ProphetNetForCausalLM(ProphetNetPreTrainedModel):
     @replace_return_docstrings(output_type=ProphetNetDecoderLMOutput, config_class=_CONFIG_FOR_DOC)
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        encoder_hidden_states=None,
-        encoder_attention_mask=None,
-        head_mask=None,
-        cross_attn_head_mask=None,
-        past_key_values=None,
-        inputs_embeds=None,
-        labels=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,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        cross_attn_head_mask: Optional[torch.Tensor] = None,
+        past_key_values: Optional[Tuple[Tuple[torch.Tensor]]] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[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, ProphetNetDecoderLMOutput]:
         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