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/tvlt/configuration_tvlt.py

@@ -69,7 +69,7 @@ class TvltConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         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-6):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
         qkv_bias (`bool`, *optional*, defaults to `True`):
             Whether to add a bias to the queries, keys and values.

src/transformers/models/tvlt/feature_extraction_tvlt.py

@@ -41,14 +41,14 @@ class TvltFeatureExtractor(SequenceFeatureExtractor):
             Number of audio channels.
         patch_size (`List[int]` *optional*, defaults to `[16, 16]`):
             The patch size of audio patch embedding.
-        feature_size (`int`, defaults to 128):
+        feature_size (`int`, *optional*, defaults to 128):
             The frequency length of audio spectrogram.
-        sampling_rate (`int`, defaults to 44100):
+        sampling_rate (`int`, *optional*, defaults to 44100):
             The sampling rate at which the audio files should be digitalized expressed in Hertz (Hz).
-        hop_length_to_sampling_rate (`int`, defaults to 86):
+        hop_length_to_sampling_rate (`int`, *optional*, defaults to 86):
             Hop length is length of the overlaping windows for the STFT used to obtain the Mel Frequency coefficients.
             For example, with sampling rate 44100, the hop length is 512, with 44100 / 512 = 86
-        n_fft (`int`, defaults to 2048):
+        n_fft (`int`, *optional*, defaults to 2048):
             Size of the Fourier transform.
         padding_value (`float`, *optional*, defaults to 0.0):
             Padding value used to pad the audio. Should correspond to silences.

src/transformers/models/videomae/image_processing_videomae.py

@@ -71,7 +71,7 @@ class VideoMAEImageProcessor(BaseImageProcessor):
             Size of the output image after resizing. The shortest edge of the image will be resized to
             `size["shortest_edge"]` while maintaining the aspect ratio of the original image. Can be overriden by
             `size` 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 overridden by the `resample` parameter in the
             `preprocess` method.
         do_center_crop (`bool`, *optional*, defaults to `True`):

src/transformers/models/vilt/image_processing_vilt.py

@@ -132,7 +132,7 @@ class ViltImageProcessor(BaseImageProcessor):
         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/vilt/processing_vilt.py

@@ -32,9 +32,9 @@ class ViltProcessor(ProcessorMixin):
     docstring of [`~ViltProcessor.__call__`] and [`~ViltProcessor.decode`] for more information.
 
     Args:
-        image_processor (`ViltImageProcessor`):
+        image_processor (`ViltImageProcessor`, *optional*):
             An instance of [`ViltImageProcessor`]. The image processor is a required input.
-        tokenizer (`BertTokenizerFast`):
+        tokenizer (`BertTokenizerFast`, *optional*):
             An instance of ['BertTokenizerFast`]. The tokenizer is a required input.
     """
     attributes = ["image_processor", "tokenizer"]

src/transformers/models/vision_text_dual_encoder/configuration_vision_text_dual_encoder.py

@@ -34,10 +34,6 @@ class VisionTextDualEncoderConfig(PretrainedConfig):
     documentation from [`PretrainedConfig`] for more information.
 
     Args:
-        text_config (`dict`):
-            Dictionary of configuration options that defines text model config.
-        vision_config (`dict`):
-            Dictionary of configuration options that defines vison model config.
         projection_dim (`int`, *optional*, defaults to 512):
             Dimentionality of text and vision projection layers.
         logit_scale_init_value (`float`, *optional*, defaults to 2.6592):

src/transformers/models/vision_text_dual_encoder/processing_vision_text_dual_encoder.py

@@ -32,9 +32,9 @@ class VisionTextDualEncoderProcessor(ProcessorMixin):
     information.
 
     Args:
-        image_processor ([`AutoImageProcessor`]):
+        image_processor ([`AutoImageProcessor`], *optional*):
             The image processor is a required input.
-        tokenizer ([`PreTrainedTokenizer`]):
+        tokenizer ([`PreTrainedTokenizer`], *optional*):
             The tokenizer is a required input.
     """
     attributes = ["image_processor", "tokenizer"]

src/transformers/models/vit/configuration_vit.py

@@ -63,15 +63,15 @@ class ViTConfig(PretrainedConfig):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         layer_norm_eps (`float`, *optional*, defaults to 1e-12):
             The epsilon used by the layer normalization layers.
-        image_size (`int`, *optional*, defaults to `224`):
+        image_size (`int`, *optional*, defaults to 224):
             The size (resolution) of each image.
-        patch_size (`int`, *optional*, defaults to `16`):
+        patch_size (`int`, *optional*, defaults to 16):
             The size (resolution) of each patch.
-        num_channels (`int`, *optional*, defaults to `3`):
+        num_channels (`int`, *optional*, defaults to 3):
             The number of input channels.
         qkv_bias (`bool`, *optional*, defaults to `True`):
             Whether to add a bias to the queries, keys and values.
-        encoder_stride (`int`, `optional`, defaults to 16):
+        encoder_stride (`int`, *optional*, defaults to 16):
            Factor to increase the spatial resolution by in the decoder head for masked image modeling.
 
     Example:

src/transformers/models/vit/image_processing_vit.py

@@ -49,7 +49,7 @@ class ViTImageProcessor(BaseImageProcessor):
         size (`dict`, *optional*, defaults to `{"height": 224, "width": 224}`):
             Size of the output image after resizing. Can be overridden by the `size` parameter 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 overridden by the `resample` parameter in the
             `preprocess` method.
         do_rescale (`bool`, *optional*, defaults to `True`):

src/transformers/models/vit_hybrid/configuration_vit_hybrid.py

@@ -40,6 +40,8 @@ class ViTHybridConfig(PretrainedConfig):
     documentation from [`PretrainedConfig`] for more information.
 
     Args:
+        backbone_config (`Union[Dict[str, Any], PretrainedConfig]`, *optional*):
+            The configuration of the backbone in a dictionary or the config object of the backbone.
         hidden_size (`int`, *optional*, defaults to 768):
             Dimensionality of the encoder layers and the pooler layer.
         num_hidden_layers (`int`, *optional*, defaults to 12):
@@ -51,9 +53,9 @@ class ViTHybridConfig(PretrainedConfig):
         hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
-        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
+        hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
-        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
+        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
@@ -65,12 +67,10 @@ class ViTHybridConfig(PretrainedConfig):
             The size (resolution) of each patch.
         num_channels (`int`, *optional*, defaults to 3):
             The number of input channels.
-        qkv_bias (`bool`, *optional*, defaults to `True`):
-            Whether to add a bias to the queries, keys and values.
-        backbone_config (`Union[Dict[str, Any], PretrainedConfig]`, *optional*, defaults to `None`):
-            The configuration of the backbone in a dictionary or the config object of the backbone.
         backbone_featmap_shape (`List[int]`, *optional*, defaults to `[1, 1024, 24, 24]`):
             Used only for the `hybrid` embedding type. The shape of the feature maps of the backbone.
+        qkv_bias (`bool`, *optional*, defaults to `True`):
+            Whether to add a bias to the queries, keys and values.
 
     Example:
 

src/transformers/models/vit_mae/configuration_vit_mae.py

@@ -65,7 +65,7 @@ class ViTMAEConfig(PretrainedConfig):
             The number of input channels.
         qkv_bias (`bool`, *optional*, defaults to `True`):
             Whether to add a bias to the queries, keys and values.
-        decoder_num_attention_heads (`int`, *optional*, defaults to 12):
+        decoder_num_attention_heads (`int`, *optional*, defaults to 16):
             Number of attention heads for each attention layer in the decoder.
         decoder_hidden_size (`int`, *optional*, defaults to 512):
             Dimensionality of the decoder.

src/transformers/models/vitdet/configuration_vitdet.py

@@ -53,7 +53,7 @@ class VitDetConfig(BackboneConfigMixin, PretrainedConfig):
             The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         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-6):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
         image_size (`int`, *optional*, defaults to 224):
             The size (resolution) of each image.
@@ -67,9 +67,9 @@ class VitDetConfig(BackboneConfigMixin, PretrainedConfig):
             Whether to add a bias to the queries, keys and values.
         drop_path_rate (`float`, *optional*, defaults to 0.0):
             Stochastic depth rate.
-        window_block_indices (`List[int]`, *optional*):
+        window_block_indices (`List[int]`, *optional*, defaults to `[]`):
             List of indices of blocks that should have window attention instead of regular global self-attention.
-        residual_block_indices (`List[int]`, *optional*):
+        residual_block_indices (`List[int]`, *optional*, defaults to `[]`):
             List of indices of blocks that should have an extra residual block after the MLP.
         use_absolute_position_embeddings (`bool`, *optional*, defaults to `True`):
             Whether to add absolute position embeddings to the patch embeddings.

src/transformers/models/vitmatte/configuration_vitmatte.py

@@ -44,7 +44,7 @@ class VitMatteConfig(PretrainedConfig):
             The configuration of the backbone model.
         hidden_size (`int`, *optional*, defaults to 384):
             The number of input channels of the decoder.
-        batch_norm_eps (`float`, *optional*, defaults to 1e-5):
+        batch_norm_eps (`float`, *optional*, defaults to 1e-05):
             The epsilon used by the batch norm layers.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

src/transformers/models/vitmatte/image_processing_vitmatte.py

@@ -46,7 +46,7 @@ class VitMatteImageProcessor(BaseImageProcessor):
         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):
+        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_normalize (`bool`, *optional*, defaults to `True`):

src/transformers/models/vits/configuration_vits.py

@@ -48,7 +48,7 @@ class VitsConfig(PretrainedConfig):
             Number of attention heads for each attention layer in the Transformer encoder.
         window_size (`int`, *optional*, defaults to 4):
             Window size for the relative positional embeddings in the attention layers of the Transformer encoder.
-        use_bias (`bool`, *optional*, defaults to `True`)
+        use_bias (`bool`, *optional*, defaults to `True`):
             Whether to use bias in the key, query, value projection layers in the Transformer encoder.
         ffn_dim (`int`, *optional*, defaults to 768):
             Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
@@ -72,7 +72,7 @@ class VitsConfig(PretrainedConfig):
             The dropout ratio for activations inside the fully connected layer.
         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-5):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-05):
             The epsilon used by the layer normalization layers.
         use_stochastic_duration_prediction (`bool`, *optional*, defaults to `True`):
             Whether to use the stochastic duration prediction module or the regular duration predictor.

src/transformers/models/vivit/image_processing_vivit.py

@@ -73,7 +73,7 @@ class VivitImageProcessor(BaseImageProcessor):
             Size of the output image after resizing. The shortest edge of the image will be resized to
             `size["shortest_edge"]` while maintaining the aspect ratio of the original image. Can be overriden by
             `size` 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 overridden by the `resample` parameter in the
             `preprocess` method.
         do_center_crop (`bool`, *optional*, defaults to `True`):
@@ -85,7 +85,7 @@ class VivitImageProcessor(BaseImageProcessor):
         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 1/127.5):
+        rescale_factor (`int` or `float`, *optional*, defaults to `1/127.5`):
             Defines the scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter
             in the `preprocess` method.
         offset (`bool`, *optional*, defaults to `True`):

src/transformers/models/whisper/tokenization_whisper.py

@@ -219,7 +219,7 @@ class WhisperTokenizer(PreTrainedTokenizer):
     This tokenizer inherits from [`PreTrainedTokenizer`] which contains some of the main methods. Users should refer to
     the superclass for more information regarding such methods.
 
-     Args:
+    Args:
         vocab_file (`str`):
             Path to the vocabulary file.
         merges_file (`str`):

src/transformers/models/x_clip/processing_x_clip.py

@@ -30,9 +30,9 @@ class XCLIPProcessor(ProcessorMixin):
     [`~XCLIPProcessor.__call__`] and [`~XCLIPProcessor.decode`] for more information.
 
     Args:
-        image_processor ([`VideoMAEImageProcessor`]):
+        image_processor ([`VideoMAEImageProcessor`], *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/xglm/tokenization_xglm.py

@@ -83,11 +83,6 @@ class XGLMTokenizer(PreTrainedTokenizer):
             token instead.
         pad_token (`str`, *optional*, defaults to `"<pad>"`):
             The token used for padding, for example when batching sequences of different lengths.
-        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 used by the tokenizer.
         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/xlm/tokenization_xlm.py

@@ -571,7 +571,7 @@ class XLMTokenizer(PreTrainedTokenizer):
         mask_token (`str`, *optional*, defaults to `"<special1>"`):
             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 `["<special0>","<special1>","<special2>","<special3>","<special4>","<special5>","<special6>","<special7>","<special8>","<special9>"]`):
+        additional_special_tokens (`List[str]`, *optional*, defaults to `['<special0>', '<special1>', '<special2>', '<special3>', '<special4>', '<special5>', '<special6>', '<special7>', '<special8>', '<special9>']`):
             List of additional special tokens.
         lang2id (`Dict[str, int]`, *optional*):
             Dictionary mapping languages string identifiers to their IDs.