Add type hints for ConvBert model (#16377)

* Add missing type hints for ConvBERT flavored models.

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

src/transformers/models/convbert/modeling_convbert.py

@@ -18,6 +18,7 @@
 import math
 import os
 from operator import attrgetter
+from typing import Optional, Tuple, Union
 
 import torch
 import torch.utils.checkpoint
@@ -902,17 +903,17 @@ class ConvBertForMaskedLM(ConvBertPreTrainedModel):
     )
     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.LongTensor] = None,
+        attention_mask: Optional[torch.FloatTensor] = None,
+        token_type_ids: Optional[torch.LongTensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        head_mask: Optional[torch.FloatTensor] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = 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, ...,
@@ -1006,17 +1007,17 @@ class ConvBertForSequenceClassification(ConvBertPreTrainedModel):
     )
     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.LongTensor] = None,
+        attention_mask: Optional[torch.FloatTensor] = None,
+        token_type_ids: Optional[torch.LongTensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        head_mask: Optional[torch.FloatTensor] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = 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, ...,
@@ -1104,17 +1105,17 @@ class ConvBertForMultipleChoice(ConvBertPreTrainedModel):
     )
     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.LongTensor] = None,
+        attention_mask: Optional[torch.FloatTensor] = None,
+        token_type_ids: Optional[torch.LongTensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        head_mask: Optional[torch.FloatTensor] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = 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, ...,
@@ -1200,17 +1201,17 @@ class ConvBertForTokenClassification(ConvBertPreTrainedModel):
     )
     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.LongTensor] = None,
+        attention_mask: Optional[torch.FloatTensor] = None,
+        token_type_ids: Optional[torch.LongTensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        head_mask: Optional[torch.FloatTensor] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = 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]`.
@@ -1278,18 +1279,18 @@ class ConvBertForQuestionAnswering(ConvBertPreTrainedModel):
     )
     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.LongTensor] = None,
+        attention_mask: Optional[torch.FloatTensor] = None,
+        token_type_ids: Optional[torch.LongTensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        head_mask: Optional[torch.FloatTensor] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        start_positions: Optional[torch.LongTensor] = None,
+        end_positions: Optional[torch.LongTensor] = 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/convbert/modeling_tf_convbert.py

@@ -15,6 +15,9 @@
 """ TF 2.0 ConvBERT model."""
 
 
+from typing import Optional, Tuple, Union
+
+import numpy as np
 import tensorflow as tf
 
 from ...activations_tf import get_tf_activation
@@ -28,6 +31,7 @@ from ...modeling_tf_outputs import (
 )
 from ...modeling_tf_utils import (
     TFMaskedLanguageModelingLoss,
+    TFModelInputType,
     TFMultipleChoiceLoss,
     TFPreTrainedModel,
     TFQuestionAnsweringLoss,
@@ -891,19 +895,19 @@ class TFConvBertForMaskedLM(TFConvBertPreTrainedModel, TFMaskedLanguageModelingL
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=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,
+        token_type_ids: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        position_ids: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        head_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        inputs_embeds: Optional[tf.Tensor] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        labels: Optional[tf.Tensor] = None,
+        training: Optional[bool] = False,
         **kwargs,
-    ):
+    ) -> Union[Tuple, TFMaskedLMOutput]:
         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, ...,
@@ -1015,19 +1019,19 @@ class TFConvBertForSequenceClassification(TFConvBertPreTrainedModel, TFSequenceC
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=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,
+        token_type_ids: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        position_ids: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        head_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        inputs_embeds: Optional[tf.Tensor] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        labels: Optional[tf.Tensor] = None,
+        training: Optional[bool] = False,
         **kwargs,
-    ):
+    ) -> Union[Tuple, TFSequenceClassifierOutput]:
         r"""
         labels (`tf.Tensor` of shape `(batch_size,)`, *optional*):
             Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
@@ -1124,19 +1128,19 @@ class TFConvBertForMultipleChoice(TFConvBertPreTrainedModel, TFMultipleChoiceLos
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=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,
+        token_type_ids: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        position_ids: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        head_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        inputs_embeds: Optional[tf.Tensor] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        labels: Optional[tf.Tensor] = None,
+        training: Optional[bool] = False,
         **kwargs,
-    ):
+    ) -> Union[Tuple, TFMultipleChoiceModelOutput]:
         r"""
         labels (`tf.Tensor` of shape `(batch_size,)`, *optional*):
             Labels for computing the multiple choice classification loss. Indices should be in `[0, ..., num_choices]`
@@ -1261,19 +1265,19 @@ class TFConvBertForTokenClassification(TFConvBertPreTrainedModel, TFTokenClassif
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=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,
+        token_type_ids: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        position_ids: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        head_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        inputs_embeds: Optional[tf.Tensor] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        labels: Optional[tf.Tensor] = None,
+        training: Optional[bool] = False,
         **kwargs,
-    ):
+    ) -> Union[Tuple, TFTokenClassifierOutput]:
         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]`.
@@ -1355,20 +1359,20 @@ class TFConvBertForQuestionAnswering(TFConvBertPreTrainedModel, TFQuestionAnswer
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        token_type_ids=None,
-        position_ids=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,
+        token_type_ids: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        position_ids: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        head_mask: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        inputs_embeds: Optional[tf.Tensor] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        start_positions: Optional[tf.Tensor] = None,
+        end_positions: Optional[tf.Tensor] = None,
+        training: Optional[bool] = False,
         **kwargs,
-    ):
+    ) -> Union[Tuple, TFQuestionAnsweringModelOutput]:
         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.