Add a check regarding the number of occurrences of ``` (#18389)

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

src/transformers/models/speech_to_text/modeling_speech_to_text.py

@@ -663,8 +663,8 @@ SPEECH_TO_TEXT_INPUTS_DOCSTRING = r"""
 
             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)`. decoder_inputs_embeds (`torch.FloatTensor`
-            of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*): Optionally, instead of passing
+            `decoder_input_ids` of shape `(batch_size, sequence_length)`. decoder_inputs_embeds (`torch.FloatTensor` of
+            shape `(batch_size, target_sequence_length, hidden_size)`, *optional*): Optionally, instead of passing
             `decoder_input_ids` you can choose to directly pass an embedded representation. If `past_key_values` is
             used, optionally only the last `decoder_inputs_embeds` have to be input (see `past_key_values`). This is
             useful if you want more control over how to convert `decoder_input_ids` indices into associated vectors
@@ -965,8 +965,8 @@ class Speech2TextDecoder(Speech2TextPreTrainedModel):
 
                 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 (`torch.FloatTensor`
-                of shape `(batch_size, sequence_length, hidden_size)`, *optional*): Optionally, instead of passing
+                all `decoder_input_ids` of shape `(batch_size, sequence_length)`. inputs_embeds (`torch.FloatTensor` 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.

src/transformers/models/speech_to_text/modeling_tf_speech_to_text.py

@@ -1002,11 +1002,11 @@ class TFSpeech2TextDecoder(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 into associated vectors than the model's internal
-                embedding lookup matrix.
+                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
                 returned tensors for more detail.

src/transformers/models/speech_to_text_2/modeling_speech_to_text_2.py

@@ -572,8 +572,8 @@ class Speech2Text2Decoder(Speech2Text2PreTrainedModel):
 
                 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 (`torch.FloatTensor`
-                of shape `(batch_size, sequence_length, hidden_size)`, *optional*): Optionally, instead of passing
+                all `decoder_input_ids` of shape `(batch_size, sequence_length)`. inputs_embeds (`torch.FloatTensor` 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.

src/transformers/models/xglm/modeling_xglm.py

@@ -90,11 +90,11 @@ XGLM_INPUTS_DOCSTRING = r"""
             blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
 
             If `past_key_values` are used, the user can optionally input only the last `input_ids` (those that don't
-            have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
-            ``input_ids``` of shape `(batch_size, sequence_length)`. inputs_embeds (`torch.FloatTensor` 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.
+            have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `input_ids`
+            of shape `(batch_size, sequence_length)`. inputs_embeds (`torch.FloatTensor` 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.
         inputs_embeds (`torch.FloatTensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*):
             Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. If
             `past_key_values` is used, optionally only the last `inputs_embeds` have to be input (see

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

@@ -2136,7 +2136,7 @@ class {{cookiecutter.camelcase_modelname}}PreTrainedModel(PreTrainedModel):
 
             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 (`torch.FloatTensor` 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
+            instead of all `decoder_input_ids` of shape `(batch_size, sequence_length)`. inputs_embeds (`torch.FloatTensor` 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.
         decoder_inputs_embeds (`torch.FloatTensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*):
             Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded
@@ -2483,7 +2483,7 @@ class {{cookiecutter.camelcase_modelname}}Decoder({{cookiecutter.camelcase_model
 
                 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,
+                shape `(batch_size, 1)` instead of all `decoder_input_ids` of shape `(batch_size,
                 sequence_length)`. inputs_embeds (`torch.FloatTensor` 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*):

utils/prepare_for_doc_test.py

@@ -92,6 +92,9 @@ def process_doc_file(code_file, add_new_line=True):
 
     # fmt: off
     splits = code.split("```")
+    if len(splits) % 2 != 1:
+        raise ValueError("The number of occurrences of ``` should be an even number.")
+
     splits = [s if i % 2 == 0 else process_code_block(s, add_new_line=add_new_line) for i, s in enumerate(splits)]
     clean_code = "```".join(splits)
     # fmt: on