Fix some docs what layerdrop does (#23691)

* Fix some docs what layerdrop does

* Update src/transformers/models/data2vec/configuration_data2vec_audio.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Fix more docs

---------
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

src/transformers/models/pegasus_x/configuration_pegasus_x.py

@@ -70,10 +70,10 @@ class PegasusXConfig(PretrainedConfig):
             just in case (e.g., 512 or 1024 or 2048).
         init_std (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        encoder_layerdrop: (`float`, *optional*, defaults to 0.0):
+        encoder_layerdrop (`float`, *optional*, defaults to 0.0):
             The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
             for more details.
-        decoder_layerdrop: (`float`, *optional*, defaults to 0.0):
+        decoder_layerdrop (`float`, *optional*, defaults to 0.0):
             The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
             for more details.
         use_cache (`bool`, *optional*, defaults to `True`):

src/transformers/models/rag/modeling_rag.py

@@ -1430,7 +1430,7 @@ class RagTokenForGeneration(RagPreTrainedModel):
                 priority: 1) from the `generation_config.json` model file, if it exists; 2) from the model
                 configuration. Please note that unspecified parameters will inherit [`~generation.GenerationConfig`]'s
                 default values, whose documentation should be checked to parameterize generation.
-            prefix_allowed_tokens_fn: (`Callable[[int, torch.Tensor], List[int]]`, *optional*):
+            prefix_allowed_tokens_fn (`Callable[[int, torch.Tensor], List[int]]`, *optional*):
                 If provided, this function constraints the beam search to allowed tokens only at each step. If not
                 provided no constraint is applied. This function takes 2 arguments `inputs_ids` and the batch ID
                 `batch_id`. It has to return a list with the allowed tokens for the next generation step conditioned on

src/transformers/models/rag/retrieval_rag.py

@@ -573,10 +573,10 @@ class RagRetriever:
         Retrieves documents for specified `question_hidden_states`.
 
         Args:
-            question_input_ids: (`List[List[int]]`) batch of input ids
+            question_input_ids (`List[List[int]]`) batch of input ids
             question_hidden_states (`np.ndarray` of shape `(batch_size, vector_size)`:
                 A batch of query vectors to retrieve with.
-            prefix: (`str`, *optional*):
+            prefix (`str`, *optional*):
                 The prefix used by the generator's tokenizer.
             n_docs (`int`, *optional*):
                 The number of docs retrieved per query.

src/transformers/models/realm/modeling_realm.py

@@ -726,7 +726,7 @@ class RealmReaderOutput(ModelOutput):
             The index of the retrieved span candidates in which the predicted answer is most likely.
         start_pos (`torch.IntTensor` of shape `()`):
             Predicted answer starting position in *RealmReader*'s inputs.
-        end_pos: (`torch.IntTensor` of shape `()`):
+        end_pos (`torch.IntTensor` of shape `()`):
             Predicted answer ending position in *RealmReader*'s inputs.
         hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
             Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer) of

src/transformers/models/sew/configuration_sew.py

@@ -63,6 +63,9 @@ class SEWConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         final_dropout (`float`, *optional*, defaults to 0.1):
             The dropout probability for the final projection layer of [`SEWForCTC`].
+        layerdrop (`float`, *optional*, defaults to 0.1):
+            The LayerDrop probability. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more
+            details.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         layer_norm_eps (`float`, *optional*, defaults to 1e-12):

src/transformers/models/unispeech/configuration_unispeech.py

@@ -65,6 +65,9 @@ class UniSpeechConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         final_dropout (`float`, *optional*, defaults to 0.1):
             The dropout probability for the final projection layer of [`UniSpeechForCTC`].
+        layerdrop (`float`, *optional*, defaults to 0.1):
+            The LayerDrop probability. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more
+            details.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         layer_norm_eps (`float`, *optional*, defaults to 1e-12):

src/transformers/models/unispeech_sat/configuration_unispeech_sat.py

@@ -66,6 +66,9 @@ class UniSpeechSatConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         final_dropout (`float`, *optional*, defaults to 0.1):
             The dropout probability for the final projection layer of [`UniSpeechSatForCTC`].
+        layerdrop (`float`, *optional*, defaults to 0.1):
+            The LayerDrop probability. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more
+            details.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         layer_norm_eps (`float`, *optional*, defaults to 1e-12):

src/transformers/models/wav2vec2/configuration_wav2vec2.py

@@ -63,6 +63,9 @@ class Wav2Vec2Config(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         final_dropout (`float`, *optional*, defaults to 0.1):
             The dropout probability for the final projection layer of [`Wav2Vec2ForCTC`].
+        layerdrop (`float`, *optional*, defaults to 0.1):
+            The LayerDrop probability. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more
+            details.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         layer_norm_eps (`float`, *optional*, defaults to 1e-12):

src/transformers/models/wav2vec2_conformer/configuration_wav2vec2_conformer.py

@@ -65,6 +65,9 @@ class Wav2Vec2ConformerConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         final_dropout (`float`, *optional*, defaults to 0.1):
             The dropout probability for the final projection layer of [`Wav2Vec2ConformerForCTC`].
+        layerdrop (`float`, *optional*, defaults to 0.1):
+            The LayerDrop probability. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more
+            details.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         layer_norm_eps (`float`, *optional*, defaults to 1e-12):

src/transformers/models/wavlm/configuration_wavlm.py

@@ -62,6 +62,9 @@ class WavLMConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         final_dropout (`float`, *optional*, defaults to 0.1):
             The dropout probability for the final projection layer of [`WavLMForCTC`].
+        layerdrop (`float`, *optional*, defaults to 0.1):
+            The LayerDrop probability. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more
+            details.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         layer_norm_eps (`float`, *optional*, defaults to 1e-12):

src/transformers/optimization_tf.py

@@ -117,9 +117,9 @@ def create_optimizer(
             The beta2 to use in Adam.
         adam_epsilon (`float`, *optional*, defaults to 1e-8):
             The epsilon to use in Adam.
-        adam_clipnorm: (`float`, *optional*, defaults to `None`):
+        adam_clipnorm (`float`, *optional*, defaults to `None`):
             If not `None`, clip the gradient norm for each weight tensor to this value.
-        adam_global_clipnorm: (`float`, *optional*, defaults to `None`)
+        adam_global_clipnorm (`float`, *optional*, defaults to `None`)
             If not `None`, clip gradient norm to this value. When using this argument, the norm is computed over all
             weight tensors, as if they were concatenated into a single vector.
         weight_decay_rate (`float`, *optional*, defaults to 0):

src/transformers/pipelines/audio_utils.py

@@ -119,7 +119,7 @@ def ffmpeg_microphone_live(
             The length of the striding to be used. Stride is used to provide context to a model on the (left, right) of
             an audio sample but without using that part to actually make the prediction. Setting this does not change
             the length of the chunk.
-        format_for_conversion: (`str`, defalts to `f32le`)
+        format_for_conversion (`str`, defalts to `f32le`)
             The name of the format of the audio samples to be returned by ffmpeg. The standard is `f32le`, `s16le`
             could also be used.
     Return:

src/transformers/pipelines/base.py

@@ -514,7 +514,7 @@ class PipelineDataFormat:
         Creates an instance of the right subclass of [`~pipelines.PipelineDataFormat`] depending on `format`.
 
         Args:
-            format: (`str`):
+            format (`str`):
                 The format of the desired pipeline. Acceptable values are `"json"`, `"csv"` or `"pipe"`.
             output_path (`str`, *optional*):
                 Where to save the outgoing data.

src/transformers/tokenization_utils_base.py

@@ -2093,7 +2093,7 @@ class PreTrainedTokenizerBase(SpecialTokensMixin, PushToHubMixin):
 
                 If `True`, will save the tokenizer in legacy format. If the "slow" tokenizer doesn't exits, a value
                 error is raised.
-            filename_prefix: (`str`, *optional*):
+            filename_prefix (`str`, *optional*):
                 A prefix to add to the names of the files saved by the tokenizer.
             push_to_hub (`bool`, *optional*, defaults to `False`):
                 Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the

src/transformers/training_args_tf.py

@@ -66,7 +66,7 @@ class TFTrainingArguments(TrainingArguments):
             The batch size per GPU/TPU core/CPU for training.
         per_device_eval_batch_size (`int`, *optional*, defaults to 8):
             The batch size per GPU/TPU core/CPU for evaluation.
-        gradient_accumulation_steps: (`int`, *optional*, defaults to 1):
+        gradient_accumulation_steps (`int`, *optional*, defaults to 1):
             Number of updates steps to accumulate the gradients for, before performing a backward/update pass.
 
             <Tip warning={true}>

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

@@ -107,10 +107,10 @@ class {{cookiecutter.camelcase_modelname}}Config(PretrainedConfig):
             just in case (e.g., 512 or 1024 or 2048).
         init_std (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        encoder_layerdrop: (`float`, *optional*, defaults to 0.0):
+        encoder_layerdrop (`float`, *optional*, defaults to 0.0):
             The LayerDrop probability for the encoder. See the [LayerDrop paper](see
             https://arxiv.org/abs/1909.11556) for more details.
-        decoder_layerdrop: (`float`, *optional*, defaults to 0.0):
+        decoder_layerdrop (`float`, *optional*, defaults to 0.0):
             The LayerDrop probability for the decoder. See the [LayerDrop paper](see
             https://arxiv.org/abs/1909.11556) for more details.
         use_cache (`bool`, *optional*, defaults to `True`):