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/maskformer/image_processing_maskformer.py

@@ -358,20 +358,17 @@ class MaskFormerImageProcessor(BaseImageProcessor):
             sequence like `(width, height)`, output size will be matched to this. If size is an int, smaller edge of
             the image will be matched to this number. i.e, if `height > width`, then image will be rescaled to `(size *
             height / width, size)`.
-        max_size (`int`, *optional*, defaults to 1333):
-            The largest size an image dimension can have (otherwise it's capped). Only has an effect if `do_resize` is
-            set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BILINEAR`):
+        size_divisor (`int`, *optional*, defaults to 32):
+            Some backbones need images divisible by a certain number. If not passed, it defaults to the value used in
+            Swin Transformer.
+        resample (`int`, *optional*, defaults to `Resampling.BILINEAR`):
             An optional resampling filter. This can be one of `PIL.Image.Resampling.NEAREST`,
             `PIL.Image.Resampling.BOX`, `PIL.Image.Resampling.BILINEAR`, `PIL.Image.Resampling.HAMMING`,
             `PIL.Image.Resampling.BICUBIC` or `PIL.Image.Resampling.LANCZOS`. Only has an effect if `do_resize` is set
             to `True`.
-        size_divisor (`int`, *optional*, defaults to 32):
-            Some backbones need images divisible by a certain number. If not passed, it defaults to the value used in
-            Swin Transformer.
         do_rescale (`bool`, *optional*, defaults to `True`):
             Whether to rescale the input to a certain `scale`.
-        rescale_factor (`float`, *optional*, defaults to 1/ 255):
+        rescale_factor (`float`, *optional*, defaults to `1/ 255`):
             Rescale the input by the given factor. Only has an effect if `do_rescale` is set to `True`.
         do_normalize (`bool`, *optional*, defaults to `True`):
             Whether or not to normalize the input with mean and standard deviation.

src/transformers/models/mgp_str/configuration_mgp_str.py

@@ -62,7 +62,7 @@ class MgpstrConfig(PretrainedConfig):
             Whether to add a bias to the queries, keys and values.
         distilled (`bool`, *optional*, defaults to `False`):
             Model includes a distillation token and head as in DeiT models.
-        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.
         drop_rate (`float`, *optional*, defaults to 0.0):
             The dropout probability for all fully connected layers in the embeddings, encoder.

src/transformers/models/mgp_str/processing_mgp_str.py

@@ -44,9 +44,9 @@ class MgpstrProcessor(ProcessorMixin):
     [`~MgpstrProcessor.__call__`] and [`~MgpstrProcessor.batch_decode`] for more information.
 
     Args:
-        image_processor (`ViTImageProcessor`):
+        image_processor (`ViTImageProcessor`, *optional*):
             An instance of `ViTImageProcessor`. The image processor is a required input.
-        tokenizer ([`MgpstrTokenizer`]):
+        tokenizer ([`MgpstrTokenizer`], *optional*):
             The tokenizer is a required input.
     """
     attributes = ["image_processor", "char_tokenizer"]

src/transformers/models/mgp_str/tokenization_mgp_str.py

@@ -52,7 +52,7 @@ class MgpstrTokenizer(PreTrainedTokenizer):
             The beginning of sequence token.
         eos_token (`str`, *optional*, defaults to `"[s]"`):
             The end of sequence token.
-        pad_token (`str` or `tokenizers.AddedToken`, *optional*, , defaults to `"[GO]"`):
+        pad_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"[GO]"`):
             A special token used to make arrays of tokens the same size for batching purpose. Will then be ignored by
             attention mechanisms or loss computation.
     """

src/transformers/models/mobilenet_v1/configuration_mobilenet_v1.py

@@ -55,7 +55,7 @@ class MobileNetV1Config(PretrainedConfig):
             All layers will have at least this many channels.
         hidden_act (`str` or `function`, *optional*, defaults to `"relu6"`):
             The non-linear activation function (function or string) in the Transformer encoder and convolution layers.
-        tf_padding (`bool`, `optional`, defaults to `True`):
+        tf_padding (`bool`, *optional*, defaults to `True`):
             Whether to use TensorFlow padding rules on the convolution layers.
         classifier_dropout_prob (`float`, *optional*, defaults to 0.999):
             The dropout ratio for attached classifiers.

src/transformers/models/mobilenet_v2/configuration_mobilenet_v2.py

@@ -64,16 +64,16 @@ class MobileNetV2Config(PretrainedConfig):
             the input dimensions by a factor of 32. If `output_stride` is 8 or 16, the model uses dilated convolutions
             on the depthwise layers instead of regular convolutions, so that the feature maps never become more than 8x
             or 16x smaller than the input image.
-        first_layer_is_expansion (`bool`, `optional`, defaults to `True`):
+        first_layer_is_expansion (`bool`, *optional*, defaults to `True`):
             True if the very first convolution layer is also the expansion layer for the first expansion block.
-        finegrained_output (`bool`, `optional`, defaults to `True`):
+        finegrained_output (`bool`, *optional*, defaults to `True`):
             If true, the number of output channels in the final convolution layer will stay large (1280) even if
             `depth_multiplier` is less than 1.
         hidden_act (`str` or `function`, *optional*, defaults to `"relu6"`):
             The non-linear activation function (function or string) in the Transformer encoder and convolution layers.
-        tf_padding (`bool`, `optional`, defaults to `True`):
+        tf_padding (`bool`, *optional*, defaults to `True`):
             Whether to use TensorFlow padding rules on the convolution layers.
-        classifier_dropout_prob (`float`, *optional*, defaults to 0.999):
+        classifier_dropout_prob (`float`, *optional*, defaults to 0.8):
             The dropout ratio for attached classifiers.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
@@ -105,7 +105,7 @@ class MobileNetV2Config(PretrainedConfig):
         depth_multiplier=1.0,
         depth_divisible_by=8,
         min_depth=8,
-        expand_ratio=6,
+        expand_ratio=6.0,
         output_stride=32,
         first_layer_is_expansion=True,
         finegrained_output=True,

src/transformers/models/mobilevit/configuration_mobilevit.py

@@ -74,7 +74,7 @@ class MobileViTConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the Transformer encoder and convolution layers.
         conv_kernel_size (`int`, *optional*, defaults to 3):
             The size of the convolutional kernel in the MobileViT layer.
-        output_stride (`int`, `optional`, defaults to 32):
+        output_stride (`int`, *optional*, defaults to 32):
             The ratio of the spatial resolution of the output to the resolution of the input image.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout probabilitiy for all fully connected layers in the Transformer encoder.
@@ -84,11 +84,11 @@ class MobileViTConfig(PretrainedConfig):
             The dropout ratio for attached classifiers.
         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.
         qkv_bias (`bool`, *optional*, defaults to `True`):
             Whether to add a bias to the queries, keys and values.
-        aspp_out_channels (`int`, `optional`, defaults to 256):
+        aspp_out_channels (`int`, *optional*, defaults to 256):
             Number of output channels used in the ASPP layer for semantic segmentation.
         atrous_rates (`List[int]`, *optional*, defaults to `[6, 12, 18]`):
             Dilation (atrous) factors used in the ASPP layer for semantic segmentation.

src/transformers/models/mobilevit/image_processing_mobilevit.py

@@ -59,7 +59,7 @@ class MobileViTImageProcessor(BaseImageProcessor):
         size (`Dict[str, int]` *optional*, defaults to `{"shortest_edge": 224}`):
             Controls the 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`):
             Defines the 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/mobilevitv2/configuration_mobilevitv2.py

@@ -54,15 +54,15 @@ class MobileViTV2Config(PretrainedConfig):
             The non-linear activation function (function or string) in the Transformer encoder and convolution layers.
         conv_kernel_size (`int`, *optional*, defaults to 3):
             The size of the convolutional kernel in the MobileViTV2 layer.
-        output_stride (`int`, `optional`, defaults to 32):
+        output_stride (`int`, *optional*, defaults to 32):
             The ratio of the spatial resolution of the output to the resolution of the input image.
         classifier_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for attached classifiers.
         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.
-        aspp_out_channels (`int`, `optional`, defaults to 512):
+        aspp_out_channels (`int`, *optional*, defaults to 512):
             Number of output channels used in the ASPP layer for semantic segmentation.
         atrous_rates (`List[int]`, *optional*, defaults to `[6, 12, 18]`):
             Dilation (atrous) factors used in the ASPP layer for semantic segmentation.
@@ -74,13 +74,13 @@ class MobileViTV2Config(PretrainedConfig):
             The number of attention blocks in each MobileViTV2Layer
         base_attn_unit_dims (`List[int]`, *optional*, defaults to `[128, 192, 256]`):
             The base multiplier for dimensions of attention blocks in each MobileViTV2Layer
-        width_multiplier (`float`, *optional*, defaults to 1.0)
+        width_multiplier (`float`, *optional*, defaults to 1.0):
             The width multiplier for MobileViTV2.
-        ffn_multiplier (`int`, *optional*, defaults to 2)
+        ffn_multiplier (`int`, *optional*, defaults to 2):
             The FFN multiplier for MobileViTV2.
-        attn_dropout (`float`, *optional*, defaults to 0.0)
+        attn_dropout (`float`, *optional*, defaults to 0.0):
             The dropout in the attention layer.
-        ffn_dropout (`float`, *optional*, defaults to 0.0)
+        ffn_dropout (`float`, *optional*, defaults to 0.0):
             The dropout between FFN layers.
 
     Example:

src/transformers/models/mpt/configuration_mpt.py

@@ -145,17 +145,17 @@ class MptConfig(PretrainedConfig):
             the `inputs_ids` passed when calling [`MptModel`]. Check [this
             discussion](https://huggingface.co/bigscience/mpt/discussions/120#633d28389addb8530b406c2a) on how the
             `vocab_size` has been defined.
-        resid_pdrop (`float`, *optional*, defaults to 0.1):
+        resid_pdrop (`float`, *optional*, defaults to 0.0):
             The dropout probability applied to the attention output before combining with residual.
-        layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
+        layer_norm_epsilon (`float`, *optional*, defaults to 1e-05):
             The epsilon to use in the layer normalization layers.
-        emb_pdrop (`float`, *optional*, defaults to 0.1):
+        emb_pdrop (`float`, *optional*, defaults to 0.0):
             The dropout probability for the embedding layer.
-        learned_pos_emb (`bool`, *optional*, defaults to `False`):
+        learned_pos_emb (`bool`, *optional*, defaults to `True`):
             Whether to use learned positional embeddings.
         attn_config (`dict`, *optional*):
             A dictionary used to configure the model's attention module.
-        init_device (`str`, *optional*):
+        init_device (`str`, *optional*, defaults to `"cpu"`):
             The device to use for parameter initialization. Defined for backward compatibility
         logit_scale (`float`, *optional*):
             If not None, scale the logits by this value.
@@ -169,7 +169,7 @@ class MptConfig(PretrainedConfig):
         norm_type (`str`, *optional*, defaults to `"low_precision_layernorm"`):
             Type of layer norm to use. All MPT models uses the same layer norm implementation. Defined for backward
             compatibility.
-        use_cache (`bool`, *optional*, defaults to `True`):
+        use_cache (`bool`, *optional*, defaults to `False`):
             Whether or not the model should return the last key/values attentions (not used by all models).
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

src/transformers/models/nat/configuration_nat.py

@@ -44,9 +44,9 @@ class NatConfig(BackboneConfigMixin, PretrainedConfig):
             The number of input channels.
         embed_dim (`int`, *optional*, defaults to 64):
             Dimensionality of patch embedding.
-        depths (`List[int]`, *optional*, defaults to `[2, 2, 6, 2]`):
+        depths (`List[int]`, *optional*, defaults to `[3, 4, 6, 5]`):
             Number of layers in each level of the encoder.
-        num_heads (`List[int]`, *optional*, defaults to `[3, 6, 12, 24]`):
+        num_heads (`List[int]`, *optional*, defaults to `[2, 4, 8, 16]`):
             Number of attention heads in each layer of the Transformer encoder.
         kernel_size (`int`, *optional*, defaults to 7):
             Neighborhood Attention kernel size.
@@ -65,7 +65,7 @@ class NatConfig(BackboneConfigMixin, PretrainedConfig):
             `"selu"` and `"gelu_new"` are supported.
         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):
+        layer_norm_eps (`float`, *optional*, defaults to 1e-05):
             The epsilon used by the layer normalization layers.
         layer_scale_init_value (`float`, *optional*, defaults to 0.0):
             The initial value for the layer scale. Disabled if <=0.

src/transformers/models/nougat/image_processing_nougat.py

@@ -66,7 +66,7 @@ class NougatImageProcessor(BaseImageProcessor):
             `do_resize` in the `preprocess` method.
         size (`Dict[str, int]` *optional*, defaults to `{"height": 896, "width": 672}`):
             Size of the image after resizing. Can be overridden 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 `resample` in the `preprocess` method.
         do_thumbnail (`bool`, *optional*, defaults to `True`):
             Whether to resize the image using thumbnail method.

src/transformers/models/nougat/tokenization_nougat_fast.py

@@ -383,10 +383,10 @@ class NougatTokenizerFast(PreTrainedTokenizerFast):
     methods for postprocessing the generated text.
 
     Args:
-        vocab_file (`str`):
+        vocab_file (`str`, *optional*):
             [SentencePiece](https://github.com/google/sentencepiece) file (generally has a .model extension) that
             contains the vocabulary necessary to instantiate a tokenizer.
-        tokenizer_file (`str`):
+        tokenizer_file (`str`, *optional*):
             [tokenizers](https://github.com/huggingface/tokenizers) file (generally has a .json extension) that
             contains everything needed to load the tokenizer.
 
@@ -394,16 +394,16 @@ class NougatTokenizerFast(PreTrainedTokenizerFast):
             Wether to cleanup spaces after decoding, cleanup consists in removing potential artifacts like extra
             spaces.
 
+        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 beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
 
         eos_token (`str`, *optional*, defaults to `"</s>"`):
             The end 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.
-
         pad_token (`str`, *optional*, defaults to `"<pad>"`):
             The token used for padding, for example when batching sequences of different lengths.
     """

src/transformers/models/oneformer/configuration_oneformer.py

@@ -42,87 +42,87 @@ class OneFormerConfig(PretrainedConfig):
     documentation from [`PretrainedConfig`] for more information.
 
     Args:
-        backbone_config (`PretrainedConfig`, *optional*, defaults to `SwinConfig`)
+        backbone_config (`PretrainedConfig`, *optional*, defaults to `SwinConfig`):
             The configuration of the backbone model.
-        ignore_value (`int`, *optional*, defaults to 255)
+        ignore_value (`int`, *optional*, defaults to 255):
             Values to be ignored in GT label while calculating loss.
-        num_queries (`int`, *optional*, defaults to 150)
+        num_queries (`int`, *optional*, defaults to 150):
             Number of object queries.
-        no_object_weight (`float`, *optional*, defaults to 0.1)
+        no_object_weight (`float`, *optional*, defaults to 0.1):
             Weight for no-object class predictions.
-        class_weight (`float`, *optional*, defaults to 2.0)
+        class_weight (`float`, *optional*, defaults to 2.0):
             Weight for Classification CE loss.
-        mask_weight (`float`, *optional*, defaults to 5.0)
+        mask_weight (`float`, *optional*, defaults to 5.0):
             Weight for binary CE loss.
-        dice_weight (`float`, *optional*, defaults to 5.0)
+        dice_weight (`float`, *optional*, defaults to 5.0):
             Weight for dice loss.
-        contrastive_weight (`float`, *optional*, defaults to 0.5)
+        contrastive_weight (`float`, *optional*, defaults to 0.5):
             Weight for contrastive loss.
-        contrastive_temperature (`float`, *optional*, defaults to 0.07)
+        contrastive_temperature (`float`, *optional*, defaults to 0.07):
             Initial value for scaling the contrastive logits.
-        train_num_points (`int`, *optional*, defaults to 12544)
+        train_num_points (`int`, *optional*, defaults to 12544):
             Number of points to sample while calculating losses on mask predictions.
-        oversample_ratio (`float`, *optional*, defaults to 3.0)
+        oversample_ratio (`float`, *optional*, defaults to 3.0):
             Ratio to decide how many points to oversample.
-        importance_sample_ratio (`float`, *optional*, defaults to 0.75)
+        importance_sample_ratio (`float`, *optional*, defaults to 0.75):
             Ratio of points that are sampled via importance sampling.
-        init_std (`float`, *optional*, defaults to 0.02)
+        init_std (`float`, *optional*, defaults to 0.02):
             Standard deviation for normal intialization.
-        init_xavier_std (`float`, *optional*, defaults to 0.02)
+        init_xavier_std (`float`, *optional*, defaults to 1.0):
             Standard deviation for xavier uniform initialization.
-        layer_norm_eps (`float`, *optional*, defaults to 1e-05)
+        layer_norm_eps (`float`, *optional*, defaults to 1e-05):
             Epsilon for layer normalization.
-        is_training (`bool`, *optional*, defaults to False)
+        is_training (`bool`, *optional*, defaults to `False`):
             Whether to run in training or inference mode.
-        use_auxiliary_loss (`bool`, *optional*, defaults to True)
+        use_auxiliary_loss (`bool`, *optional*, defaults to `True`):
             Whether to calculate loss using intermediate predictions from transformer decoder.
-        output_auxiliary_logits (`bool`, *optional*, defaults to True)
+        output_auxiliary_logits (`bool`, *optional*, defaults to `True`):
             Whether to return intermediate predictions from transformer decoder.
-        strides (`list`, *optional*, defaults to [4, 8, 16, 32])
+        strides (`list`, *optional*, defaults to `[4, 8, 16, 32]`):
             List containing the strides for feature maps in the encoder.
-        task_seq_len (`int`, *optional*, defaults to 77)
+        task_seq_len (`int`, *optional*, defaults to 77):
             Sequence length for tokenizing text list input.
-        text_encoder_width (`int`, *optional*, defaults to 256)
+        text_encoder_width (`int`, *optional*, defaults to 256):
             Hidden size for text encoder.
         text_encoder_context_length (`int`, *optional*, defaults to 77):
             Input sequence length for text encoder.
-        text_encoder_num_layers (`int`, *optional*, defaults to 6)
+        text_encoder_num_layers (`int`, *optional*, defaults to 6):
             Number of layers for transformer in text encoder.
-        text_encoder_vocab_size (`int`, *optional*, defaults to 49408)
+        text_encoder_vocab_size (`int`, *optional*, defaults to 49408):
             Vocabulary size for tokenizer.
-        text_encoder_proj_layers (`int`, *optional*, defaults to 2)
+        text_encoder_proj_layers (`int`, *optional*, defaults to 2):
             Number of layers in MLP for project text queries.
-        text_encoder_n_ctx (`int`, *optional*, defaults to 16)
+        text_encoder_n_ctx (`int`, *optional*, defaults to 16):
             Number of learnable text context queries.
-        conv_dim (`int`, *optional*, defaults to 256)
+        conv_dim (`int`, *optional*, defaults to 256):
             Feature map dimension to map outputs from the backbone.
-        mask_dim (`int`, *optional*, defaults to 256)
+        mask_dim (`int`, *optional*, defaults to 256):
             Dimension for feature maps in pixel decoder.
-        hidden_dim (`int`, *optional*, defaults to 256)
+        hidden_dim (`int`, *optional*, defaults to 256):
             Dimension for hidden states in transformer decoder.
-        encoder_feedforward_dim (`int`, *optional*, defaults to 1024)
+        encoder_feedforward_dim (`int`, *optional*, defaults to 1024):
             Dimension for FFN layer in pixel decoder.
-        norm (`str`, *optional*, defaults to `GN`)
+        norm (`str`, *optional*, defaults to `"GN"`):
             Type of normalization.
-        encoder_layers (`int`, *optional*, defaults to 6)
+        encoder_layers (`int`, *optional*, defaults to 6):
             Number of layers in pixel decoder.
-        decoder_layers (`int`, *optional*, defaults to 10)
+        decoder_layers (`int`, *optional*, defaults to 10):
             Number of layers in transformer decoder.
-        use_task_norm (`bool`, *optional*, defaults to `True`)
+        use_task_norm (`bool`, *optional*, defaults to `True`):
             Whether to normalize the task token.
-        num_attention_heads (`int`, *optional*, defaults to 8)
+        num_attention_heads (`int`, *optional*, defaults to 8):
             Number of attention heads in transformer layers in the pixel and transformer decoders.
-        dropout (`float`, *optional*, defaults to 0.1)
+        dropout (`float`, *optional*, defaults to 0.1):
             Dropout probability for pixel and transformer decoders.
-        dim_feedforward (`int`, *optional*, defaults to 2048)
+        dim_feedforward (`int`, *optional*, defaults to 2048):
             Dimension for FFN layer in transformer decoder.
-        pre_norm (`bool`, *optional*, defaults to `False`)
+        pre_norm (`bool`, *optional*, defaults to `False`):
             Whether to normalize hidden states before attention layers in transformer decoder.
-        enforce_input_proj (`bool`, *optional*, defaults to `False`)
+        enforce_input_proj (`bool`, *optional*, defaults to `False`):
             Whether to project hidden states in transformer decoder.
-        query_dec_layers (`int`, *optional*, defaults to 2)
+        query_dec_layers (`int`, *optional*, defaults to 2):
             Number of layers in query transformer.
-        common_stride (`int`, *optional*, defaults to 4)
+        common_stride (`int`, *optional*, defaults to 4):
             Common stride used for features in pixel decoder.
 
     Examples:

src/transformers/models/oneformer/image_processing_oneformer.py

@@ -361,17 +361,14 @@ class OneFormerImageProcessor(BaseImageProcessor):
             sequence like `(width, height)`, output size will be matched to this. If size is an int, smaller edge of
             the image will be matched to this number. i.e, if `height > width`, then image will be rescaled to `(size *
             height / width, size)`.
-        max_size (`int`, *optional*, defaults to 1333):
-            The largest size an image dimension can have (otherwise it's capped). Only has an effect if `do_resize` is
-            set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BILINEAR`):
+        resample (`int`, *optional*, defaults to `Resampling.BILINEAR`):
             An optional resampling filter. This can be one of `PIL.Image.Resampling.NEAREST`,
             `PIL.Image.Resampling.BOX`, `PIL.Image.Resampling.BILINEAR`, `PIL.Image.Resampling.HAMMING`,
             `PIL.Image.Resampling.BICUBIC` or `PIL.Image.Resampling.LANCZOS`. Only has an effect if `do_resize` is set
             to `True`.
         do_rescale (`bool`, *optional*, defaults to `True`):
             Whether to rescale the input to a certain `scale`.
-        rescale_factor (`float`, *optional*, defaults to 1/ 255):
+        rescale_factor (`float`, *optional*, defaults to `1/ 255`):
             Rescale the input by the given factor. Only has an effect if `do_rescale` is set to `True`.
         do_normalize (`bool`, *optional*, defaults to `True`):
             Whether or not to normalize the input with mean and standard deviation.
@@ -387,9 +384,9 @@ class OneFormerImageProcessor(BaseImageProcessor):
             Whether or not to decrement all label values of segmentation maps by 1. Usually used for datasets where 0
             is used for background, and background itself is not included in all classes of a dataset (e.g. ADE20k).
             The background label will be replaced by `ignore_index`.
-        repo_path (`str`, defaults to `shi-labs/oneformer_demo`):
+        repo_path (`str`, defaults to `shi-labs/oneformer_demo`, *optional*, defaults to `"shi-labs/oneformer_demo"`):
             Dataset repository on huggingface hub containing the JSON file with class information for the dataset.
-        class_info_file (`str`):
+        class_info_file (`str`, *optional*):
             JSON file containing class information for the dataset. It is stored inside on the `repo_path` dataset
             repository.
         num_text (`int`, *optional*):

src/transformers/models/openai/configuration_openai.py

@@ -56,7 +56,7 @@ class OpenAIGPTConfig(PretrainedConfig):
             The dropout ratio for the embeddings.
         attn_pdrop (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention.
-        layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
+        layer_norm_epsilon (`float`, *optional*, defaults to 1e-05):
             The epsilon to use in the layer normalization layers
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
@@ -91,8 +91,6 @@ class OpenAIGPTConfig(PretrainedConfig):
             [`OpenAIGPTDoubleHeadsModel`].
 
             The dropout ratio to be used after the projection and activation.
-        use_cache (`bool`, *optional*, defaults to `True`):
-            Whether or not the model should return the last key/values attentions (not used by all models).
 
 
     Examples:

src/transformers/models/owlvit/configuration_owlvit.py

@@ -171,13 +171,13 @@ class OwlViTVisionConfig(PretrainedConfig):
         hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` ``"quick_gelu"` are supported.
-        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.
         attention_dropout (`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.
-        initializer_factor (`float``, *optional*, defaults to 1):
+        initializer_factor (`float``, *optional*, defaults to 1.0):
             A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
             testing).
 

src/transformers/models/owlvit/image_processing_owlvit.py

@@ -102,7 +102,7 @@ class OwlViTImageProcessor(BaseImageProcessor):
             The size to use for resizing the image. Only has an effect if `do_resize` is set to `True`. If `size` is a
             sequence like (h, w), output size will be matched to this. If `size` is an int, then image will be resized
             to (size, size).
-        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BICUBIC`):
+        resample (`int`, *optional*, defaults to `Resampling.BICUBIC`):
             An optional resampling filter. This can be one of `PIL.Image.Resampling.NEAREST`,
             `PIL.Image.Resampling.BOX`, `PIL.Image.Resampling.BILINEAR`, `PIL.Image.Resampling.HAMMING`,
             `PIL.Image.Resampling.BICUBIC` or `PIL.Image.Resampling.LANCZOS`. Only has an effect if `do_resize` is set

src/transformers/models/owlvit/processing_owlvit.py

@@ -33,9 +33,9 @@ class OwlViTProcessor(ProcessorMixin):
     [`~OwlViTProcessor.__call__`] and [`~OwlViTProcessor.decode`] for more information.
 
     Args:
-        image_processor ([`OwlViTImageProcessor`]):
+        image_processor ([`OwlViTImageProcessor`], *optional*):
             The image processor is a required input.
-        tokenizer ([`CLIPTokenizer`, `CLIPTokenizerFast`]):
+        tokenizer ([`CLIPTokenizer`, `CLIPTokenizerFast`], *optional*):
             The tokenizer is a required input.
     """
     attributes = ["image_processor", "tokenizer"]

src/transformers/models/perceiver/configuration_perceiver.py

@@ -65,7 +65,7 @@ class PerceiverConfig(PretrainedConfig):
         v_channels (`int`, *optional*):
             Dimension to project the values before applying attention in the cross-attention and self-attention layers
             of the encoder. Will default to preserving the dimension of the queries if not specified.
-        cross_attention_shape_for_attention (`str`, *optional*, defaults to `'kv'`):
+        cross_attention_shape_for_attention (`str`, *optional*, defaults to `"kv"`):
             Dimension to use when downsampling the queries and keys in the cross-attention layer of the encoder.
         self_attention_widening_factor (`int`, *optional*, defaults to 1):
             Dimension of the feed-forward layer in the cross-attention layer of the Transformer encoder.
@@ -89,7 +89,7 @@ class PerceiverConfig(PretrainedConfig):
             this to something large just in case (e.g., 512 or 1024 or 2048).
         image_size (`int`, *optional*, defaults to 56):
             Size of the images after preprocessing, for [`PerceiverForImageClassificationLearned`].
-        train_size (`List[int]`, *optional*, defaults to [368, 496]):
+        train_size (`List[int]`, *optional*, defaults to `[368, 496]`):
             Training size of the images for the optical flow model.
         num_frames (`int`, *optional*, defaults to 16):
             Number of video frames used for the multimodal autoencoding model.
@@ -97,11 +97,11 @@ class PerceiverConfig(PretrainedConfig):
             Number of audio samples per frame for the multimodal autoencoding model.
         samples_per_patch (`int`, *optional*, defaults to 16):
             Number of audio samples per patch when preprocessing the audio for the multimodal autoencoding model.
-        output_num_channels (`int`, *optional*, defaults to 512):
-            Number of output channels for each modalitiy decoder.
         output_shape (`List[int]`, *optional*, defaults to `[1, 16, 224, 224]`):
             Shape of the output (batch_size, num_frames, height, width) for the video decoder queries of the multimodal
             autoencoding model. This excludes the channel dimension.
+        output_num_channels (`int`, *optional*, defaults to 512):
+            Number of output channels for each modalitiy decoder.
 
     Example: