Added Type hints for XLM TF (#19333)

* Update modeling_tf_xlm.py

* Updates

* Update src/transformers/models/xlm/modeling_tf_xlm.py

* Update src/transformers/models/xlm/modeling_tf_xlm.py

* Update src/transformers/models/xlm/modeling_tf_xlm.py

* Update src/transformers/models/xlm/modeling_tf_xlm.py

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

src/transformers/models/xlm/modeling_tf_xlm.py

@@ -19,7 +19,7 @@
 import itertools
 import warnings
 from dataclasses import dataclass
-from typing import Dict, Optional, Tuple
+from typing import Dict, Optional, Tuple, Union
 
 import numpy as np
 import tensorflow as tf
@@ -33,6 +33,7 @@ from ...modeling_tf_outputs import (
     TFTokenClassifierOutput,
 )
 from ...modeling_tf_utils import (
+    TFModelInputType,
     TFMultipleChoiceLoss,
     TFPreTrainedModel,
     TFQuestionAnsweringLoss,
@@ -844,19 +845,19 @@ class TFXLMWithLMHeadModel(TFXLMPreTrainedModel):
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        langs=None,
-        token_type_ids=None,
-        position_ids=None,
-        lengths=None,
-        cache=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,
+        langs: 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,
+        lengths: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        cache: Optional[Dict[str, 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: bool = False,
     ):
         transformer_outputs = self.transformer(
             input_ids=input_ids,
@@ -916,20 +917,20 @@ class TFXLMForSequenceClassification(TFXLMPreTrainedModel, TFSequenceClassificat
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        langs=None,
-        token_type_ids=None,
-        position_ids=None,
-        lengths=None,
-        cache=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,
+        langs: 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,
+        lengths: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        cache: Optional[Dict[str, 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: bool = False,
     ):
         r"""
         labels (`tf.Tensor` of shape `(batch_size,)`, *optional*):
@@ -1023,20 +1024,20 @@ class TFXLMForMultipleChoice(TFXLMPreTrainedModel, TFMultipleChoiceLoss):
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        langs=None,
-        token_type_ids=None,
-        position_ids=None,
-        lengths=None,
-        cache=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,
+        langs: 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,
+        lengths: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        cache: Optional[Dict[str, 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: bool = False,
     ):
         if input_ids is not None:
             num_choices = shape_list(input_ids)[1]
@@ -1147,20 +1148,20 @@ class TFXLMForTokenClassification(TFXLMPreTrainedModel, TFTokenClassificationLos
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        langs=None,
-        token_type_ids=None,
-        position_ids=None,
-        lengths=None,
-        cache=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,
+        langs: 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,
+        lengths: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        cache: Optional[Dict[str, 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: bool = False,
     ):
         r"""
         labels (`tf.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
@@ -1232,21 +1233,21 @@ class TFXLMForQuestionAnsweringSimple(TFXLMPreTrainedModel, TFQuestionAnsweringL
     )
     def call(
         self,
-        input_ids=None,
-        attention_mask=None,
-        langs=None,
-        token_type_ids=None,
-        position_ids=None,
-        lengths=None,
-        cache=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,
+        langs: 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,
+        lengths: Optional[Union[np.ndarray, tf.Tensor]] = None,
+        cache: Optional[Dict[str, 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: bool = False,
     ):
         r"""
         start_positions (`tf.Tensor` of shape `(batch_size,)`, *optional*):