Check the repo consistency in model templates test (#15141)

* Check the repo consistency in model templates test

* Fix doc template

* Fix docstrings

* Fix last docstring

.github/workflows/model-templates.yml

@@ -61,7 +61,7 @@ jobs:
       - name: Run style changes
         run: |
           git fetch origin master:master
-          make style && make quality
+          make style && make quality && make repo-consistency
 
       - name: Failure short reports
         if: ${{ always() }}

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

@@ -2119,8 +2119,9 @@ class Flax{{cookiecutter.camelcase_modelname}}PreTrainedModel(FlaxPreTrainedMode
         r"""
         Returns:
 
-        Example::
+        Example:
 
+        ```python
         >>> from transformers import {{cookiecutter.camelcase_modelname}}Tokenizer, Flax{{cookiecutter.camelcase_modelname}}ForConditionalGeneration
 
         >>> model = Flax{{cookiecutter.camelcase_modelname}}ForConditionalGeneration.from_pretrained('{{cookiecutter.checkpoint_identifier}}')
@@ -2129,7 +2130,7 @@ class Flax{{cookiecutter.camelcase_modelname}}PreTrainedModel(FlaxPreTrainedMode
         >>> text = "My friends are cool but they eat too many carbs."
         >>> inputs = tokenizer(text, max_length=1024, return_tensors='np')
         >>> encoder_outputs = model.encode(**inputs)
-        """
+        ```"""
         output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
         output_hidden_states = (
             output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
@@ -2184,8 +2185,9 @@ class Flax{{cookiecutter.camelcase_modelname}}PreTrainedModel(FlaxPreTrainedMode
         r"""
         Returns:
 
-        Example::
+        Example:
 
+        ```python
         >>> from transformers import {{cookiecutter.camelcase_modelname}}Tokenizer, Flax{{cookiecutter.camelcase_modelname}}ForConditionalGeneration
 
         >>> model = Flax{{cookiecutter.camelcase_modelname}}ForConditionalGeneration.from_pretrained('{{cookiecutter.checkpoint_identifier}}')
@@ -2200,7 +2202,7 @@ class Flax{{cookiecutter.camelcase_modelname}}PreTrainedModel(FlaxPreTrainedMode
 
         >>> outputs = model.decode(decoder_input_ids, encoder_outputs)
         >>> last_decoder_hidden_states = outputs.last_hidden_state
-        """
+        ```"""
         output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
         output_hidden_states = (
             output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
@@ -2450,8 +2452,9 @@ class Flax{{cookiecutter.camelcase_modelname}}ForConditionalGeneration(Flax{{coo
         r"""
         Returns:
 
-        Example::
+        Example:
 
+        ```python
         >>> from transformers import {{cookiecutter.camelcase_modelname}}Tokenizer, Flax{{cookiecutter.camelcase_modelname}}ForConditionalGeneration
 
         >>> model = Flax{{cookiecutter.camelcase_modelname}}ForConditionalGeneration.from_pretrained('{{cookiecutter.checkpoint_identifier}}')
@@ -2466,7 +2469,7 @@ class Flax{{cookiecutter.camelcase_modelname}}ForConditionalGeneration(Flax{{coo
 
         >>> outputs = model.decode(decoder_input_ids, encoder_outputs)
         >>> logits = outputs.logits
-        """
+        ```"""
         output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
         output_hidden_states = (
             output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states

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

@@ -878,7 +878,7 @@ class TF{{cookiecutter.camelcase_modelname}}PreTrainedModel(TFPreTrainedModel):
 
 {{cookiecutter.uppercase_modelname}}_INPUTS_DOCSTRING = r"""
     Args:
-        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})`):
+        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
@@ -925,7 +925,7 @@ class TF{{cookiecutter.camelcase_modelname}}PreTrainedModel(TFPreTrainedModel):
         return_dict (`bool`, *optional*):
             Whether or not to return a [`~file_utils.ModelOutput`] instead of a plain tuple. This
             argument can be used in eager mode, in graph mode the value will always be set to True.
-        training (`bool`, *optional*, defaults to `False``):
+        training (`bool`, *optional*, defaults to `False`):
             Whether or not to use the model in training mode (some modules like dropout modules have different
             behaviors between training and evaluation).
 """
@@ -2611,8 +2611,11 @@ class TF{{cookiecutter.camelcase_modelname}}Decoder(tf.keras.layers.Layer):
 
                 If `past_key_values` are used, the user can optionally input only the last
                 `decoder_input_ids` (those that don't have their past key value states given to this model) of
-                shape `(batch_size, 1)` instead of all ``decoder_input_ids``` of shape `(batch_size,
-                sequence_length)`. inputs_embeds (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*): Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices
+                shape `(batch_size, 1)` instead of all `decoder_input_ids` of shape `(batch_size,
+                sequence_length)`.
+            inputs_embeds (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
+                Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation.
+                This is useful if you want more control over how to convert `input_ids` indices
                 into associated vectors than the model's internal embedding lookup matrix.
             output_attentions (`bool`, *optional*):
                 Whether or not to return the attentions tensors of all attention layers. See `attentions` under
@@ -3085,8 +3088,9 @@ class TF{{cookiecutter.camelcase_modelname}}ForConditionalGeneration(TF{{cookiec
         """
         Returns:
 
-        Examples::
+        Examples:
 
+        ```python
         >>> from transformers import {{cookiecutter.camelcase_modelname}}Tokenizer, TF{{cookiecutter.camelcase_modelname}}ForConditionalGeneration
         >>> import tensorflow as tf
         >>> mname = '{{cookiecutter.checkpoint_identifier}}'
@@ -3097,7 +3101,7 @@ class TF{{cookiecutter.camelcase_modelname}}ForConditionalGeneration(TF{{cookiec
         >>> logits = model(inputs=batch.input_ids).logits
         >>> probs = tf.nn.softmax(logits[0])
         >>> # probs[5] is associated with the mask token
-        """
+        ```"""
         inputs = input_processing(
             func=self.call,
             config=self.config,

templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/{{cookiecutter.lowercase_modelname}}.mdx

@@ -127,7 +127,7 @@ This model was contributed by [INSERT YOUR HF USERNAME HERE](<https://huggingfac
     - call
 
 
-## TF{{cookiecutter.camelcase_modelname}}ForCausalLM[[autodoc]] 
+## TF{{cookiecutter.camelcase_modelname}}ForCausalLM
 
 [[autodoc]] TF{{cookiecutter.camelcase_modelname}}ForCausalLM
     - call