Docstring check (#26052)

* Fix number of minimal calls to the Hub with peft integration

* Alternate design

* And this way?

* Revert

* Nits to fix

* Add util

* Print when changes are made

* Add list to ignore

* Add more rules

* Manual fixes

* deal with kwargs

* deal with enum defaults

* avoid many digits for floats

* Manual fixes

* Fix regex

* Fix regex

* Auto fix

* Style

* Apply script

* Add ignored list

* Add check that templates are filled

* Adding to CI checks

* Add back semi-fix

* Ignore more objects

* More auto-fixes

* Ignore missing objects

* Remove temp semi-fix

* Fixes

* Update src/transformers/models/pvt/configuration_pvt.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update utils/check_docstrings.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update src/transformers/utils/quantization_config.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Deal with float defaults

* Fix small defaults

* Address review comment

* Treat

* Post-rebase cleanup

* Address review comment

* Update src/transformers/models/deprecated/mctct/configuration_mctct.py
Co-authored-by: Lysandre Debut <lysandre.debut@reseau.eseo.fr>

* Address review comment

---------
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
Co-authored-by: Lysandre Debut <lysandre.debut@reseau.eseo.fr>

src/transformers/models/beit/configuration_beit.py

@@ -41,7 +41,7 @@ class BeitConfig(PretrainedConfig):
     [microsoft/beit-base-patch16-224-pt22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k) architecture.
 
     Args:
-        vocab_size (`int`, *optional*, defaults to 8092):
+        vocab_size (`int`, *optional*, defaults to 8192):
             Vocabulary size of the BEiT model. Defines the number of different image tokens that can be used during
             pre-training.
         hidden_size (`int`, *optional*, defaults to 768):

src/transformers/models/beit/image_processing_beit.py

@@ -57,7 +57,7 @@ class BeitImageProcessor(BaseImageProcessor):
         size (`Dict[str, int]` *optional*, defaults to `{"height": 256, "width": 256}`):
             Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess`
             method.
-        resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
+        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`):
             Resampling filter to use if resizing the image. Can be overridden by the `resample` parameter in the
             `preprocess` method.
         do_center_crop (`bool`, *optional*, defaults to `True`):
@@ -67,12 +67,12 @@ class BeitImageProcessor(BaseImageProcessor):
         crop_size (`Dict[str, int]`, *optional*, defaults to `{"height": 224, "width": 224}`):
             Desired output size when applying center-cropping. Only has an effect if `do_center_crop` is set to `True`.
             Can be overridden by the `crop_size` parameter in the `preprocess` method.
-        do_rescale (`bool`, *optional*, defaults to `True`):
-            Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale`
-            parameter in the `preprocess` method.
         rescale_factor (`int` or `float`, *optional*, defaults to `1/255`):
             Scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the
             `preprocess` method.
+        do_rescale (`bool`, *optional*, defaults to `True`):
+            Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale`
+            parameter in the `preprocess` method.
         do_normalize (`bool`, *optional*, defaults to `True`):
             Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess`
             method.

src/transformers/models/bertweet/tokenization_bertweet.py

@@ -77,7 +77,7 @@ class BertweetTokenizer(PreTrainedTokenizer):
             Path to the vocabulary file.
         merges_file (`str`):
             Path to the merges file.
-        normalization (`bool`, *optional*, defaults to `False`)
+        normalization (`bool`, *optional*, defaults to `False`):
             Whether or not to apply a normalization preprocess.
         bos_token (`str`, *optional*, defaults to `"<s>"`):
             The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.

src/transformers/models/big_bird/tokenization_big_bird.py

@@ -60,25 +60,25 @@ class BigBirdTokenizer(PreTrainedTokenizer):
         vocab_file (`str`):
             [SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that
             contains the vocabulary necessary to instantiate a tokenizer.
-        eos_token (`str`, *optional*, defaults to `"</s>"`):
-            The end of sequence token.
-        bos_token (`str`, *optional*, defaults to `"<s>"`):
-            The begin of sequence token.
         unk_token (`str`, *optional*, defaults to `"<unk>"`):
             The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
             token instead.
+        bos_token (`str`, *optional*, defaults to `"<s>"`):
+            The begin of sequence token.
+        eos_token (`str`, *optional*, defaults to `"</s>"`):
+            The end of sequence token.
         pad_token (`str`, *optional*, defaults to `"<pad>"`):
             The token used for padding, for example when batching sequences of different lengths.
         sep_token (`str`, *optional*, defaults to `"[SEP]"`):
             The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
             sequence classification or for a text and a question for question answering. It is also used as the last
             token of a sequence built with special tokens.
-        cls_token (`str`, *optional*, defaults to `"[CLS]"`):
-            The classifier token which is used when doing sequence classification (classification of the whole sequence
-            instead of per-token classification). It is the first token of the sequence when built with special tokens.
         mask_token (`str`, *optional*, defaults to `"[MASK]"`):
             The token used for masking values. This is the token used when training this model with masked language
             modeling. This is the token which the model will try to predict.
+        cls_token (`str`, *optional*, defaults to `"[CLS]"`):
+            The classifier token which is used when doing sequence classification (classification of the whole sequence
+            instead of per-token classification). It is the first token of the sequence when built with special tokens.
         sp_model_kwargs (`dict`, *optional*):
             Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for
             SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things,

src/transformers/models/biogpt/configuration_biogpt.py

@@ -72,12 +72,13 @@ class BioGptConfig(PretrainedConfig):
             Please refer to the paper about LayerDrop: https://arxiv.org/abs/1909.11556 for further details
         activation_dropout (`float`, *optional*, defaults to 0.0):
             The dropout ratio for activations inside the fully connected layer.
-        pad_token_id (`int`, *optional*, defaults to 1)
+        pad_token_id (`int`, *optional*, defaults to 1):
             Padding token id.
-        bos_token_id (`int`, *optional*, defaults to 0)
+        bos_token_id (`int`, *optional*, defaults to 0):
             Beginning of stream token id.
-        eos_token_id (`int`, *optional*, defaults to 2)
+        eos_token_id (`int`, *optional*, defaults to 2):
             End of stream token id.
+
     Example:
 
     ```python

src/transformers/models/bit/configuration_bit.py

@@ -52,7 +52,7 @@ class BitConfig(BackboneConfigMixin, PretrainedConfig):
             are supported.
         global_padding (`str`, *optional*):
             Padding strategy to use for the convolutional layers. Can be either `"valid"`, `"same"`, or `None`.
-        num_groups (`int`, *optional*, defaults to `32`):
+        num_groups (`int`, *optional*, defaults to 32):
             Number of groups used for the `BitGroupNormActivation` layers.
         drop_path_rate (`float`, *optional*, defaults to 0.0):
             The drop path rate for the stochastic depth.

src/transformers/models/blenderbot_small/tokenization_blenderbot_small.py

@@ -85,9 +85,9 @@ class BlenderbotSmallTokenizer(PreTrainedTokenizer):
         unk_token (`str`, *optional*, defaults to `"__unk__"`):
             The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
             token instead.
-        pad_token (`str`, *optional*, defaults to `"__pad__"`):
+        pad_token (`str`, *optional*, defaults to `"__null__"`):
             The token used for padding, for example when batching sequences of different lengths.
-        **kwargs
+        kwargs (*optional*):
             Additional keyword arguments passed along to [`PreTrainedTokenizer`]
     """
 

src/transformers/models/blip/configuration_blip.py

@@ -295,7 +295,7 @@ class BlipConfig(PretrainedConfig):
             Dimentionality of text and vision projection layers.
         logit_scale_init_value (`float`, *optional*, defaults to 2.6592):
             The inital value of the *logit_scale* paramter. Default is used as per the original BLIP implementation.
-        image_text_hidden_size (`int`, *optional*, defaults to 768):
+        image_text_hidden_size (`int`, *optional*, defaults to 256):
             Dimentionality of the hidden state of the image-text fusion layer.
         kwargs (*optional*):
             Dictionary of keyword arguments.

src/transformers/models/blip/image_processing_blip.py

@@ -53,7 +53,7 @@ class BlipImageProcessor(BaseImageProcessor):
         size (`dict`, *optional*, defaults to `{"height": 384, "width": 384}`):
             Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess`
             method.
-        resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
+        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`):
             Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. Can be
             overridden by the `resample` parameter in the `preprocess` method.
         do_rescale (`bool`, *optional*, defaults to `True`):

src/transformers/models/bridgetower/image_processing_bridgetower.py

@@ -128,14 +128,14 @@ class BridgeTowerImageProcessor(BaseImageProcessor):
         do_resize (`bool`, *optional*, defaults to `True`):
             Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by the
             `do_resize` parameter in the `preprocess` method.
-        size (`Dict[str, int]` *optional*, defaults to `288`):
+        size (`Dict[str, int]` *optional*, defaults to 288):
             Resize the shorter side of the input to `size["shortest_edge"]`. The longer side will be limited to under
             `int((1333 / 800) * size["shortest_edge"])` while preserving the aspect ratio. Only has an effect if
             `do_resize` is set to `True`. Can be overridden by the `size` parameter in the `preprocess` method.
         size_divisor (`int`, *optional*, defaults to 32):
             The size by which to make sure both the height and width can be divided. Only has an effect if `do_resize`
             is set to `True`. Can be overridden by the `size_divisor` parameter in the `preprocess` method.
-        resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
+        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`):
             Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. Can be
             overridden by the `resample` parameter in the `preprocess` method.
         do_rescale (`bool`, *optional*, defaults to `True`):

src/transformers/models/bros/processing_bros.py

@@ -31,7 +31,7 @@ class BrosProcessor(ProcessorMixin):
     [`~BrosProcessor.__call__`] and [`~BrosProcessor.decode`] for more information.
 
     Args:
-        tokenizer (`BertTokenizerFast`):
+        tokenizer (`BertTokenizerFast`, *optional*):
             An instance of ['BertTokenizerFast`]. The tokenizer is a required input.
     """
     attributes = ["tokenizer"]

src/transformers/models/byt5/tokenization_byt5.py

@@ -48,7 +48,7 @@ class ByT5Tokenizer(PreTrainedTokenizer):
             token instead.
         pad_token (`str`, *optional*, defaults to `"<pad>"`):
             The token used for padding, for example when batching sequences of different lengths.
-        extra_ids (`int`, *optional*, defaults to 100):
+        extra_ids (`int`, *optional*, defaults to 125):
             Add a number of extra ids added to the end of the vocabulary for use as sentinels. These tokens are
             accessible as "<extra_id_{%d}>" where "{%d}" is a number between 0 and extra_ids-1. Extra tokens are
             indexed from the end of the vocabulary up to beginning ("<extra_id_0>" is the last token in the vocabulary

src/transformers/models/camembert/tokenization_camembert.py

@@ -89,7 +89,7 @@ class CamembertTokenizer(PreTrainedTokenizer):
         mask_token (`str`, *optional*, defaults to `"<mask>"`):
             The token used for masking values. This is the token used when training this model with masked language
             modeling. This is the token which the model will try to predict.
-        additional_special_tokens (`List[str]`, *optional*, defaults to `["<s>NOTUSED", "</s>NOTUSED"]`):
+        additional_special_tokens (`List[str]`, *optional*, defaults to `['<s>NOTUSED', '</s>NOTUSED']`):
             Additional special tokens used by the tokenizer.
         sp_model_kwargs (`dict`, *optional*):
             Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for

src/transformers/models/chinese_clip/processing_chinese_clip.py

@@ -31,9 +31,9 @@ class ChineseCLIPProcessor(ProcessorMixin):
     See the [`~ChineseCLIPProcessor.__call__`] and [`~ChineseCLIPProcessor.decode`] for more information.
 
     Args:
-        image_processor ([`ChineseCLIPImageProcessor`]):
+        image_processor ([`ChineseCLIPImageProcessor`], *optional*):
             The image processor is a required input.
-        tokenizer ([`BertTokenizerFast`]):
+        tokenizer ([`BertTokenizerFast`], *optional*):
             The tokenizer is a required input.
     """
     attributes = ["image_processor", "tokenizer"]

src/transformers/models/clap/configuration_clap.py

@@ -227,7 +227,7 @@ class ClapAudioConfig(PretrainedConfig):
         projection_hidden_act (`str`, *optional*, defaults to `"relu"`):
             The non-linear activation function (function or string) in the projection layer. If string, `"gelu"`,
             `"relu"`, `"silu"` and `"gelu_new"` are supported.
-        layer_norm_eps (`[type]`, *optional*, defaults to `1e-5`):
+        layer_norm_eps (`[type]`, *optional*, defaults to 1e-05):
             The epsilon used by the layer normalization layers.
         initializer_factor (`float`, *optional*, defaults to 1.0):
             A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
@@ -345,10 +345,10 @@ class ClapConfig(PretrainedConfig):
             Dictionary of configuration options used to initialize [`ClapTextConfig`].
         audio_config (`dict`, *optional*):
             Dictionary of configuration options used to initialize [`ClapAudioConfig`].
+        logit_scale_init_value (`float`, *optional*, defaults to 14.29):
+            The inital value of the *logit_scale* paramter. Default is used as per the original CLAP implementation.
         projection_dim (`int`, *optional*, defaults to 512):
             Dimentionality of text and audio projection layers.
-        logit_scale_init_value (`float`, *optional*, defaults to 2.6592):
-            The inital value of the *logit_scale* paramter. Default is used as per the original CLAP implementation.
         projection_hidden_act (`str`, *optional*, defaults to `"relu"`):
             Activation function for the projection layers.
         initializer_factor (`float`, *optional*, defaults to 1.0):

src/transformers/models/clap/feature_extraction_clap.py

@@ -41,32 +41,32 @@ class ClapFeatureExtractor(SequenceFeatureExtractor):
     Fourier Transform* (STFT) which should match pytorch's `torch.stft` equivalent.
 
     Args:
-        feature_size (`int`, defaults to 64):
+        feature_size (`int`, *optional*, defaults to 64):
             The feature dimension of the extracted Mel spectrograms. This corresponds to the number of mel filters
             (`n_mels`).
-        sampling_rate (`int`, defaults to 48_000):
+        sampling_rate (`int`, *optional*, defaults to 48000):
             The sampling rate at which the audio files should be digitalized expressed in hertz (Hz). This only serves
             to warn users if the audio fed to the feature extractor does not have the same sampling rate.
-        hop_length (`int`, defaults to 480):
+        hop_length (`int`,*optional*, defaults to 480):
             Length of the overlaping windows for the STFT used to obtain the Mel Spectrogram. The audio will be split
             in smaller `frames` with a step of `hop_length` between each frame.
-        max_length_s (`int`, defaults to 10):
+        max_length_s (`int`, *optional*, defaults to 10):
             The maximum input length of the model in seconds. This is used to pad the audio.
-        fft_window_size (`int`, defaults to 1024):
+        fft_window_size (`int`, *optional*, defaults to 1024):
             Size of the window (in samples) on which the Fourier transform is applied. This controls the frequency
             resolution of the spectrogram. 400 means that the fourrier transform is computed on windows of 400 samples.
         padding_value (`float`, *optional*, defaults to 0.0):
             Padding value used to pad the audio. Should correspond to silences.
         return_attention_mask (`bool`, *optional*, defaults to `False`):
             Whether or not the model should return the attention masks coresponding to the input.
-        frequency_min (`float`, *optional*, default to 0):
+        frequency_min (`float`, *optional*, defaults to 0):
             The lowest frequency of interest. The STFT will not be computed for values below this.
-        frequency_max (`float`, *optional*, default to 14_000):
+        frequency_max (`float`, *optional*, defaults to 14000):
             The highest frequency of interest. The STFT will not be computed for values above this.
         top_db (`float`, *optional*):
             The highest decibel value used to convert the mel spectrogram to the log scale. For more details see the
             `audio_utils.power_to_db` function
-        truncation (`str`, *optional*, default to `"fusions"`):
+        truncation (`str`, *optional*, defaults to `"fusion"`):
             Truncation pattern for long audio inputs. Two patterns are available:
                 - `fusion` will use `_random_mel_fusion`, which stacks 3 random crops from the mel spectrogram and a
                   downsampled version of the entire mel spectrogram.

src/transformers/models/clip/processing_clip.py

@@ -30,9 +30,9 @@ class CLIPProcessor(ProcessorMixin):
     [`~CLIPProcessor.__call__`] and [`~CLIPProcessor.decode`] for more information.
 
     Args:
-        image_processor ([`CLIPImageProcessor`]):
+        image_processor ([`CLIPImageProcessor`], *optional*):
             The image processor is a required input.
-        tokenizer ([`CLIPTokenizerFast`]):
+        tokenizer ([`CLIPTokenizerFast`], *optional*):
             The tokenizer is a required input.
     """
     attributes = ["image_processor", "tokenizer"]

src/transformers/models/clipseg/configuration_clipseg.py

@@ -255,7 +255,7 @@ class CLIPSegConfig(PretrainedConfig):
             Dimensionality of text and vision projection layers.
         logit_scale_init_value (`float`, *optional*, defaults to 2.6592):
             The inital value of the *logit_scale* paramter. Default is used as per the original CLIPSeg implementation.
-        extract_layers (`List[int]`, *optional*, defaults to [3, 6, 9]):
+        extract_layers (`List[int]`, *optional*, defaults to `[3, 6, 9]`):
             Layers to extract when forwarding the query image through the frozen visual backbone of CLIP.
         reduce_dim (`int`, *optional*, defaults to 64):
             Dimensionality to reduce the CLIP vision embedding.

src/transformers/models/clipseg/processing_clipseg.py

@@ -30,9 +30,9 @@ class CLIPSegProcessor(ProcessorMixin):
     [`~CLIPSegProcessor.__call__`] and [`~CLIPSegProcessor.decode`] for more information.
 
     Args:
-        image_processor ([`ViTImageProcessor`]):
+        image_processor ([`ViTImageProcessor`], *optional*):
             The image processor is a required input.
-        tokenizer ([`CLIPTokenizerFast`]):
+        tokenizer ([`CLIPTokenizerFast`], *optional*):
             The tokenizer is a required input.
     """
     attributes = ["image_processor", "tokenizer"]

src/transformers/models/convnext/image_processing_convnext.py

@@ -64,7 +64,7 @@ class ConvNextImageProcessor(BaseImageProcessor):
         crop_pct (`float` *optional*, defaults to 224 / 256):
             Percentage of the image to crop. Only has an effect if `do_resize` is `True` and size < 384. Can be
             overriden by `crop_pct` in the `preprocess` method.
-        resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`):
+        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
             Resampling filter to use if resizing the image. Can be overriden by `resample` in the `preprocess` method.
         do_rescale (`bool`, *optional*, defaults to `True`):
             Whether to rescale the image by the specified scale `rescale_factor`. Can be overriden by `do_rescale` in