Docs: change some input_ids doc reference from BertTokenizer to AutoTokenizer (#24730)

src/transformers/generation/logits_process.py

@@ -32,7 +32,7 @@ LOGITS_PROCESSOR_INPUTS_DOCSTRING = r"""
         input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.encode`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
             [`PreTrainedTokenizer.__call__`] for details.
 
             [What are input IDs?](../glossary#input-ids)

src/transformers/generation/stopping_criteria.py

@@ -17,7 +17,7 @@ STOPPING_CRITERIA_INPUTS_DOCSTRING = r"""
         input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.encode`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
             [`PreTrainedTokenizer.__call__`] for details.
 
             [What are input IDs?](../glossary#input-ids)

src/transformers/models/bart/modeling_tf_bart.py

@@ -576,7 +576,7 @@ BART_INPUTS_DOCSTRING = r"""
         input_ids (`tf.Tensor` of shape `({0})`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.encode`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
             [`PreTrainedTokenizer.__call__`] for details.
 
             [What are input IDs?](../glossary#input-ids)

src/transformers/models/bridgetower/modeling_bridgetower.py

@@ -65,7 +65,7 @@ BRIDGETOWER_START_DOCSTRING = r"""
 BRIDGETOWER_INPUTS_DOCSTRING = r"""
     Args:
         input_ids (`torch.LongTensor` of shape `({0})`):
-            Indices of input sequence tokens in the vocabulary. Indices can be obtained using [`BertTokenizer`]. See
+            Indices of input sequence tokens in the vocabulary. Indices can be obtained using [`AutoTokenizer`]. See
             [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. [What are input
             IDs?](../glossary#input-ids)
 

src/transformers/models/clip/modeling_tf_clip.py

@@ -943,7 +943,7 @@ CLIP_TEXT_INPUTS_DOCSTRING = r"""
         input_ids (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` ``Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `({0})`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
             [`PreTrainedTokenizer.encode`] for details.
 
             [What are input IDs?](../glossary#input-ids)
@@ -1000,7 +1000,7 @@ CLIP_INPUTS_DOCSTRING = r"""
         input_ids (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` ``Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `({0})`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
             [`PreTrainedTokenizer.encode`] for details.
 
             [What are input IDs?](../glossary#input-ids)

src/transformers/models/funnel/modeling_funnel.py

@@ -882,7 +882,7 @@ FUNNEL_INPUTS_DOCSTRING = r"""
         input_ids (`torch.LongTensor` of shape `({0})`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.encode`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
             [`PreTrainedTokenizer.__call__`] for details.
 
             [What are input IDs?](../glossary#input-ids)

src/transformers/models/groupvit/modeling_tf_groupvit.py

@@ -1502,7 +1502,7 @@ GROUPVIT_TEXT_INPUTS_DOCSTRING = r"""
         input_ids (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` ``Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `({0})`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
             [`PreTrainedTokenizer.encode`] for details.
 
             [What are input IDs?](../glossary#input-ids)
@@ -1560,7 +1560,7 @@ GROUPVIT_INPUTS_DOCSTRING = r"""
         input_ids (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` ``Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `({0})`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
             [`PreTrainedTokenizer.encode`] for details.
 
             [What are input IDs?](../glossary#input-ids)

src/transformers/models/led/modeling_tf_led.py

@@ -1560,7 +1560,7 @@ LED_INPUTS_DOCSTRING = r"""
         input_ids (`tf.Tensor` of shape `({0})`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.encode`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
             [`PreTrainedTokenizer.__call__`] for details.
 
             [What are input IDs?](../glossary#input-ids)

src/transformers/models/mmbt/modeling_mmbt.py

@@ -106,7 +106,7 @@ MMBT_INPUTS_DOCSTRING = r"""
             Encoder, the shape would be (batch_size, channels, height, width)
         input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`):
             Indices of input sequence tokens in the vocabulary. It does not expect [CLS] token to be added as it's
-            appended to the end of other modality embeddings. Indices can be obtained using [`BertTokenizer`]. See
+            appended to the end of other modality embeddings. Indices can be obtained using [`AutoTokenizer`]. See
             [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details.
 
             [What are input IDs?](../glossary#input-ids)

src/transformers/models/mobilebert/modeling_mobilebert.py

@@ -761,7 +761,7 @@ MOBILEBERT_INPUTS_DOCSTRING = r"""
         input_ids (`torch.LongTensor` of shape `({0})`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.encode`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
             [`PreTrainedTokenizer.__call__`] for details.
 
             [What are input IDs?](../glossary#input-ids)

src/transformers/models/t5/modeling_tf_t5.py

@@ -960,7 +960,7 @@ T5_INPUTS_DOCSTRING = r"""
             Indices of input sequence tokens in the vocabulary. T5 is a model with relative position embeddings so you
             should be able to pad the inputs on the right or the left.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
             [`PreTrainedTokenizer.encode`] for details.
 
             [What are input IDs?](../glossary#input-ids)

src/transformers/models/transfo_xl/modeling_tf_transfo_xl.py

@@ -814,7 +814,7 @@ TRANSFO_XL_INPUTS_DOCSTRING = r"""
         input_ids (`tf.Tensor` or `Numpy array` of shape `(batch_size, sequence_length)`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
+            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.__call__`] and
             [`PreTrainedTokenizer.encode`] for details.
 
             [What are input IDs?](../glossary#input-ids)

src/transformers/models/vilt/modeling_vilt.py

@@ -610,7 +610,7 @@ VILT_START_DOCSTRING = r"""
 VILT_INPUTS_DOCSTRING = r"""
     Args:
         input_ids (`torch.LongTensor` of shape `({0})`):
-            Indices of input sequence tokens in the vocabulary. Indices can be obtained using [`BertTokenizer`]. See
+            Indices of input sequence tokens in the vocabulary. Indices can be obtained using [`AutoTokenizer`]. See
             [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. [What are input
             IDs?](../glossary#input-ids)
 
@@ -665,7 +665,7 @@ VILT_INPUTS_DOCSTRING = r"""
 VILT_IMAGES_AND_TEXT_CLASSIFICATION_INPUTS_DOCSTRING = r"""
     Args:
         input_ids (`torch.LongTensor` of shape `({0})`):
-            Indices of input sequence tokens in the vocabulary. Indices can be obtained using [`BertTokenizer`]. See
+            Indices of input sequence tokens in the vocabulary. Indices can be obtained using [`AutoTokenizer`]. See
             [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. [What are input
             IDs?](../glossary#input-ids)
 

templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_tf_{{cookiecutter.lowercase_modelname}}.py

@@ -851,7 +851,7 @@ class TF{{cookiecutter.camelcase_modelname}}PreTrainedModel(TFPreTrainedModel):
         input_ids (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]`, `Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `({0})`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using [`BertTokenizer`]. See
+            Indices can be obtained using [`AutoTokenizer`]. See
             [`PreTrainedTokenizer.__call__`] and [`PreTrainedTokenizer.encode`] for
             details.