Add type hints for TFDistilBert (#16107)

* Add type hints for TFDistilBert

* Update src/transformers/models/distilbert/modeling_tf_distilbert.py
Co-authored-by: Matt <Rocketknight1@users.noreply.github.com>

src/transformers/models/distilbert/modeling_tf_distilbert.py

@@ -17,7 +17,9 @@
 """
 
 import warnings
+from typing import Optional, Tuple, Union
 
+import numpy as np
 import tensorflow as tf
 
 from ...activations_tf import get_tf_activation
@@ -37,6 +39,7 @@ from ...modeling_tf_outputs import (
 )
 from ...modeling_tf_utils import (
     TFMaskedLanguageModelingLoss,
+    TFModelInputType,
     TFMultipleChoiceLoss,
     TFPreTrainedModel,
     TFQuestionAnsweringLoss,
@@ -546,16 +549,16 @@ class TFDistilBertModel(TFDistilBertPreTrainedModel):
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        head_mask=None,
-        inputs_embeds=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-        training=False,
+        input_ids: Optional[TFModelInputType] = None,
+        attention_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        head_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        inputs_embeds: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        training: Optional[bool] = False,
         **kwargs,
-    ):
+    ) -> Union[TFBaseModelOutput, Tuple[tf.Tensor]]:
         inputs = input_processing(
             func=self.call,
             config=self.config,
@@ -661,17 +664,17 @@ class TFDistilBertForMaskedLM(TFDistilBertPreTrainedModel, TFMaskedLanguageModel
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        head_mask=None,
-        inputs_embeds=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-        labels=None,
-        training=False,
+        input_ids: Optional[TFModelInputType] = None,
+        attention_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        head_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        inputs_embeds: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        labels: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        training: Optional[bool] = False,
         **kwargs,
-    ):
+    ) -> Union[TFMaskedLMOutput, Tuple[tf.Tensor]]:
         r"""
         labels (`tf.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
             Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
@@ -762,17 +765,17 @@ class TFDistilBertForSequenceClassification(TFDistilBertPreTrainedModel, TFSeque
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        head_mask=None,
-        inputs_embeds=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-        labels=None,
-        training=False,
+        input_ids: Optional[TFModelInputType] = None,
+        attention_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        head_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        inputs_embeds: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        labels: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        training: Optional[bool] = False,
         **kwargs,
-    ):
+    ) -> Union[TFSequenceClassifierOutput, Tuple[tf.Tensor]]:
         r"""
         labels (`tf.Tensor` of shape `(batch_size,)`, *optional*):
             Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
@@ -857,17 +860,17 @@ class TFDistilBertForTokenClassification(TFDistilBertPreTrainedModel, TFTokenCla
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        head_mask=None,
-        inputs_embeds=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-        labels=None,
-        training=False,
+        input_ids: Optional[TFModelInputType] = None,
+        attention_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        head_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        inputs_embeds: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        labels: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        training: Optional[bool] = False,
         **kwargs,
-    ):
+    ) -> Union[TFTokenClassifierOutput, Tuple[tf.Tensor]]:
         r"""
         labels (`tf.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
             Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.
@@ -964,17 +967,17 @@ class TFDistilBertForMultipleChoice(TFDistilBertPreTrainedModel, TFMultipleChoic
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        head_mask=None,
-        inputs_embeds=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-        labels=None,
-        training=False,
+        input_ids: Optional[TFModelInputType] = None,
+        attention_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        head_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        inputs_embeds: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        labels: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        training: Optional[bool] = False,
         **kwargs,
-    ):
+    ) -> Union[TFMultipleChoiceModelOutput, Tuple[tf.Tensor]]:
         r"""
         labels (`tf.Tensor` of shape `(batch_size,)`, *optional*):
             Labels for computing the multiple choice classification loss. Indices should be in `[0, ..., num_choices]`
@@ -1089,18 +1092,18 @@ class TFDistilBertForQuestionAnswering(TFDistilBertPreTrainedModel, TFQuestionAn
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        head_mask=None,
-        inputs_embeds=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-        start_positions=None,
-        end_positions=None,
-        training=False,
+        input_ids: Optional[TFModelInputType] = None,
+        attention_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        head_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        inputs_embeds: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        start_positions: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        end_positions: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        training: Optional[bool] = False,
         **kwargs,
-    ):
+    ) -> Union[TFQuestionAnsweringModelOutput, Tuple[tf.Tensor]]:
         r"""
         start_positions (`tf.Tensor` of shape `(batch_size,)`, *optional*):
             Labels for position (index) of the start of the labelled span for computing the token classification loss.