Fix mismatched ` in doc & other common typos (#31516)

fix common doc typos
Co-authored-by: Jiahui Wei <jiahui.wei@tusen.ai>

src/transformers/models/align/configuration_align.py

@@ -307,9 +307,9 @@ class AlignConfig(PretrainedConfig):
         vision_config (`dict`, *optional*):
             Dictionary of configuration options used to initialize [`AlignVisionConfig`].
         projection_dim (`int`, *optional*, defaults to 640):
-            Dimentionality of text and vision projection layers.
+            Dimensionality of text and vision projection layers.
         temperature_init_value (`float`, *optional*, defaults to 1.0):
-            The inital value of the *temperature* paramter. Default is used as per the original ALIGN implementation.
+            The initial value of the *temperature* parameter. Default is used as per the original ALIGN implementation.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         kwargs (*optional*):

src/transformers/models/altclip/configuration_altclip.py

@@ -80,7 +80,7 @@ class AltCLIPTextConfig(PretrainedConfig):
             Whether or not the model should return the last key/values attentions (not used by all models). Only
             relevant if `config.is_decoder=True`.
         project_dim (`int`, *optional*, defaults to 768):
-            The dimentions of the teacher model before the mapping layer.
+            The dimensions of the teacher model before the mapping layer.
 
     Examples:
 
@@ -159,7 +159,7 @@ class AltCLIPVisionConfig(PretrainedConfig):
         intermediate_size (`int`, *optional*, defaults to 3072):
             Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
         projection_dim (`int`, *optional*, defaults to 512):
-            Dimentionality of text and vision projection layers.
+            Dimensionality of text and vision projection layers.
         num_hidden_layers (`int`, *optional*, defaults to 12):
             Number of hidden layers in the Transformer encoder.
         num_attention_heads (`int`, *optional*, defaults to 12):
@@ -172,7 +172,7 @@ class AltCLIPVisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         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):
@@ -268,9 +268,9 @@ class AltCLIPConfig(PretrainedConfig):
         vision_config (`dict`, *optional*):
             Dictionary of configuration options used to initialize [`AltCLIPVisionConfig`].
         projection_dim (`int`, *optional*, defaults to 768):
-            Dimentionality of text and vision projection layers.
+            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 CLIP implementation.
+            The initial value of the *logit_scale* parameter. Default is used as per the original CLIP implementation.
         kwargs (*optional*):
             Dictionary of keyword arguments.
 
@@ -333,7 +333,7 @@ class AltCLIPConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`text_config_dict` is provided which will be used to initialize `AltCLIPTextConfig`. The "
-                            f'value `text_config["{key}"]` will be overriden.'
+                            f'value `text_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 
@@ -365,7 +365,7 @@ class AltCLIPConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`vision_config_dict` is provided which will be used to initialize `AltCLIPVisionConfig`. "
-                            f'The value `vision_config["{key}"]` will be overriden.'
+                            f'The value `vision_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 

src/transformers/models/blip/configuration_blip.py

@@ -54,7 +54,7 @@ class BlipTextConfig(PretrainedConfig):
             just in case (e.g., 512 or 1024 or 2048).
         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"` ``"gelu"` are supported.
+            `"relu"`, `"selu"` and `"gelu_new"` `"gelu"` are supported.
         layer_norm_eps (`float`, *optional*, defaults to 1e-12):
             The epsilon used by the layer normalization layers.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
@@ -191,7 +191,7 @@ class BlipVisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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"` ``"gelu"` are supported.
+            `"relu"`, `"selu"` and `"gelu_new"` `"gelu"` are supported.
         layer_norm_eps (`float`, *optional*, defaults to 1e-5):
             The epsilon used by the layer normalization layers.
         attention_dropout (`float`, *optional*, defaults to 0.0):
@@ -280,11 +280,11 @@ class BlipConfig(PretrainedConfig):
         vision_config (`dict`, *optional*):
             Dictionary of configuration options used to initialize [`BlipVisionConfig`].
         projection_dim (`int`, *optional*, defaults to 512):
-            Dimentionality of text and vision projection layers.
+            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 BLIP implementation.
+            The initial value of the *logit_scale* parameter. Default is used as per the original BLIP implementation.
         image_text_hidden_size (`int`, *optional*, defaults to 256):
-            Dimentionality of the hidden state of the image-text fusion layer.
+            Dimensionality of the hidden state of the image-text fusion layer.
         label_smoothing (float, optional, *optional*, defaults to 0.0):
             A float in [0.0, 1.0]. Specifies the amount of smoothing when computing the loss, where 0.0 means no smoothing. The targets
             become a mixture of the original ground truth and a uniform distribution as described in

src/transformers/models/blip_2/configuration_blip_2.py

@@ -51,7 +51,7 @@ class Blip2VisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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"` ``"gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults
+            `"relu"`, `"selu"` and `"gelu_new"` `"gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults
             to 1e-5): The epsilon used by the layer normalization layers.
         attention_dropout (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.

src/transformers/models/chinese_clip/configuration_chinese_clip.py

@@ -177,7 +177,7 @@ class ChineseCLIPVisionConfig(PretrainedConfig):
         intermediate_size (`int`, *optional*, defaults to 3072):
             Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
         projection_dim (`int`, *optional*, defaults to 512):
-            Dimentionality of text and vision projection layers.
+            Dimensionality of text and vision projection layers.
         num_hidden_layers (`int`, *optional*, defaults to 12):
             Number of hidden layers in the Transformer encoder.
         num_attention_heads (`int`, *optional*, defaults to 12):
@@ -190,7 +190,7 @@ class ChineseCLIPVisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         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):
@@ -285,9 +285,9 @@ class ChineseCLIPConfig(PretrainedConfig):
         vision_config (`dict`, *optional*):
             Dictionary of configuration options used to initialize [`ChineseCLIPVisionConfig`].
         projection_dim (`int`, *optional*, defaults to 512):
-            Dimentionality of text and vision projection layers.
+            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 ChineseCLIP
+            The initial value of the *logit_scale* parameter. Default is used as per the original ChineseCLIP
             implementation.
         kwargs (*optional*):
             Dictionary of keyword arguments.
@@ -351,7 +351,7 @@ class ChineseCLIPConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`text_config_dict` is provided which will be used to initialize `ChineseCLIPTextConfig`. "
-                            f'The value `text_config["{key}"]` will be overriden.'
+                            f'The value `text_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 
@@ -383,7 +383,7 @@ class ChineseCLIPConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`vision_config_dict` is provided which will be used to initialize "
-                            f'`ChineseCLIPVisionConfig`. The value `vision_config["{key}"]` will be overriden.'
+                            f'`ChineseCLIPVisionConfig`. The value `vision_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 

src/transformers/models/clap/configuration_clap.py

@@ -342,9 +342,9 @@ class ClapConfig(PretrainedConfig):
         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.
+            The initial value of the *logit_scale* parameter. Default is used as per the original CLAP implementation.
         projection_dim (`int`, *optional*, defaults to 512):
-            Dimentionality of text and audio projection layers.
+            Dimensionality of text and audio projection layers.
         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/clip/configuration_clip.py

@@ -50,7 +50,7 @@ class CLIPTextConfig(PretrainedConfig):
         intermediate_size (`int`, *optional*, defaults to 2048):
             Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
         projection_dim (`int`, *optional*, defaults to 512):
-            Dimentionality of text and vision projection layers.
+            Dimensionality of text and vision projection layers.
         num_hidden_layers (`int`, *optional*, defaults to 12):
             Number of hidden layers in the Transformer encoder.
         num_attention_heads (`int`, *optional*, defaults to 8):
@@ -165,7 +165,7 @@ class CLIPVisionConfig(PretrainedConfig):
         intermediate_size (`int`, *optional*, defaults to 3072):
             Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
         projection_dim (`int`, *optional*, defaults to 512):
-            Dimentionality of text and vision projection layers.
+            Dimensionality of text and vision projection layers.
         num_hidden_layers (`int`, *optional*, defaults to 12):
             Number of hidden layers in the Transformer encoder.
         num_attention_heads (`int`, *optional*, defaults to 12):
@@ -178,7 +178,7 @@ class CLIPVisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         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):
@@ -274,9 +274,9 @@ class CLIPConfig(PretrainedConfig):
         vision_config (`dict`, *optional*):
             Dictionary of configuration options used to initialize [`CLIPVisionConfig`].
         projection_dim (`int`, *optional*, defaults to 512):
-            Dimentionality of text and vision projection layers.
+            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 CLIP implementation.
+            The initial value of the *logit_scale* parameter. Default is used as per the original CLIP implementation.
         kwargs (*optional*):
             Dictionary of keyword arguments.
 
@@ -340,7 +340,7 @@ class CLIPConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The "
-                            f'value `text_config["{key}"]` will be overriden.'
+                            f'value `text_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 
@@ -372,7 +372,7 @@ class CLIPConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`vision_config_dict` is provided which will be used to initialize `CLIPVisionConfig`. "
-                            f'The value `vision_config["{key}"]` will be overriden.'
+                            f'The value `vision_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 

src/transformers/models/clipseg/configuration_clipseg.py

@@ -51,7 +51,7 @@ class CLIPSegTextConfig(PretrainedConfig):
             just in case (e.g., 512 or 1024 or 2048).
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         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):
@@ -163,7 +163,7 @@ class CLIPSegVisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         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):
@@ -259,7 +259,7 @@ class CLIPSegConfig(PretrainedConfig):
         projection_dim (`int`, *optional*, defaults to 512):
             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.
+            The initial value of the *logit_scale* parameter. Default is used as per the original CLIPSeg implementation.
         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):
@@ -270,7 +270,7 @@ class CLIPSegConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         decoder_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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         decoder_intermediate_size (`int`, *optional*, defaults to 2048):
             Dimensionality of the "intermediate" (i.e., feed-forward) layers in the Transformer decoder.
         conditional_layer (`int`, *optional*, defaults to 0):
@@ -354,7 +354,7 @@ class CLIPSegConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`text_config_dict` is provided which will be used to initialize `CLIPSegTextConfig`. The "
-                            f'value `text_config["{key}"]` will be overriden.'
+                            f'value `text_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 
@@ -386,7 +386,7 @@ class CLIPSegConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`vision_config_dict` is provided which will be used to initialize `CLIPSegVisionConfig`. "
-                            f'The value `vision_config["{key}"]` will be overriden.'
+                            f'The value `vision_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 

src/transformers/models/clvp/configuration_clvp.py

@@ -351,9 +351,9 @@ class ClvpConfig(PretrainedConfig):
         decoder_config (`dict`, *optional*):
             Dictionary of configuration options used to initialize [`ClvpDecoderConfig`].
         projection_dim (`int`, *optional*, defaults to 768):
-            Dimentionality of text and speech projection layers.
+            Dimensionality of text and speech 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 CLVP implementation.
+            The initial value of the *logit_scale* parameter. Default is used as per the original CLVP implementation.
         initializer_factor (`float`, *optional*, defaults to 1.0):
             A factor for initializing all weight matrices (should be kept to 1.0, used internally for initialization
             testing).

src/transformers/models/flava/configuration_flava.py

@@ -483,9 +483,9 @@ class FlavaConfig(PretrainedConfig):
         layer_norm_eps (`float`, *optional*, defaults to 1e-12):
             The epsilon used by the layer normalization layers.
         projection_dim (`int`, *optional*, defaults to 512):
-            Dimentionality of text and image projection layers.
+            Dimensionality of text and image 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 FLAVA/CLIP
+            The initial value of the *logit_scale* parameter. Default is used as per the original FLAVA/CLIP
             implementation.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
@@ -590,7 +590,7 @@ class FlavaConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`text_config_dict` is provided which will be used to initialize `FlavaTextConfig`. The "
-                            f'value `text_config["{key}"]` will be overriden.'
+                            f'value `text_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 
@@ -622,7 +622,7 @@ class FlavaConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`image_config_dict` is provided which will be used to initialize `FlavaImageConfig`. "
-                            f'The value `image_config["{key}"]` will be overriden.'
+                            f'The value `image_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 
@@ -654,7 +654,7 @@ class FlavaConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`multimodal_config_dict` is provided which will be used to initialize "
-                            f'`FlavaMultimodalConfig`. The value `multimodal_config["{key}"]` will be overriden.'
+                            f'`FlavaMultimodalConfig`. The value `multimodal_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 
@@ -687,7 +687,7 @@ class FlavaConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`image_codebook_config_dict` is provided which will be used to initialize "
-                            f'`FlavaImageCodebookConfig`. The value `image_codebook_config["{key}"]` will be overriden.'
+                            f'`FlavaImageCodebookConfig`. The value `image_codebook_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 

src/transformers/models/git/configuration_git.py

@@ -48,7 +48,7 @@ class GitVisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         layer_norm_eps (`float`, *optional*, defaults to 1e-5):
             The epsilon used by the layer normalization layers.
         attention_dropout (`float`, *optional*, defaults to 0.0):

src/transformers/models/groupvit/configuration_groupvit.py

@@ -58,7 +58,7 @@ class GroupViTTextConfig(PretrainedConfig):
             just in case (e.g., 512 or 1024 or 2048).
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         layer_norm_eps (`float`, *optional*, defaults to 1e-5):
             The epsilon used by the layer normalization layers.
         attention_dropout (`float`, *optional*, defaults to 0.0):
@@ -169,7 +169,7 @@ class GroupViTVisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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"` ``"quick_gelu"` are supported.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         layer_norm_eps (`float`, *optional*, defaults to 1e-5):
             The epsilon used by the layer normalization layers.
         dropout (`float`, *optional*, defaults to 0.0):
@@ -281,11 +281,11 @@ class GroupViTConfig(PretrainedConfig):
         vision_config (`dict`, *optional*):
             Dictionary of configuration options used to initialize [`GroupViTVisionConfig`].
         projection_dim (`int`, *optional*, defaults to 256):
-            Dimentionality of text and vision projection layers.
+            Dimensionality of text and vision projection layers.
         projection_intermediate_dim (`int`, *optional*, defaults to 4096):
-            Dimentionality of intermediate layer of text and vision projection layers.
+            Dimensionality of intermediate layer of text and vision projection layers.
         logit_scale_init_value (`float`, *optional*, defaults to 2.6592):
-            The inital value of the *logit_scale* parameter. Default is used as per the original GroupViT
+            The initial value of the *logit_scale* parameter. Default is used as per the original GroupViT
             implementation.
         kwargs (*optional*):
             Dictionary of keyword arguments.
@@ -333,7 +333,7 @@ class GroupViTConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`text_config_dict` is provided which will be used to initialize `GroupViTTextConfig`. "
-                            f'The value `text_config["{key}"]` will be overriden.'
+                            f'The value `text_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 
@@ -365,7 +365,7 @@ class GroupViTConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`vision_config_dict` is provided which will be used to initialize `GroupViTVisionConfig`."
-                            f' The value `vision_config["{key}"]` will be overriden.'
+                            f' The value `vision_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 

src/transformers/models/idefics/configuration_idefics.py

@@ -54,7 +54,7 @@ class IdeficsVisionConfig(PretrainedConfig):
             Number of image channels.
         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"` ``"quick_gelu"` are supported.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         layer_norm_eps (`float`, *optional*, defaults to 1e-5):
             The epsilon used by the layer normalization layers.
         attention_dropout (`float`, *optional*, defaults to 0.0):

src/transformers/models/idefics2/configuration_idefics2.py

@@ -52,7 +52,7 @@ class Idefics2VisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         hidden_act (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`):
             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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
         attention_dropout (`float`, *optional*, defaults to 0.0):

src/transformers/models/instructblip/configuration_instructblip.py

@@ -51,7 +51,7 @@ class InstructBlipVisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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"` ``"gelu"` are supported. to 1e-5): The epsilon used by the layer
+            `"relu"`, `"selu"` and `"gelu_new"` `"gelu"` are supported. to 1e-5): The epsilon used by the layer
             normalization layers.
         layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.

src/transformers/models/kosmos2/configuration_kosmos2.py

@@ -170,7 +170,7 @@ class Kosmos2VisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         layer_norm_eps (`float`, *optional*, defaults to 1e-5):
             The epsilon used by the layer normalization layers.
         attention_dropout (`float`, *optional*, defaults to 0.0):

src/transformers/models/owlv2/configuration_owlv2.py

@@ -57,7 +57,7 @@ class Owlv2TextConfig(PretrainedConfig):
             just in case (e.g., 512 or 1024 or 2048).
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         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):
@@ -170,7 +170,7 @@ class Owlv2VisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         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):
@@ -267,7 +267,7 @@ class Owlv2Config(PretrainedConfig):
         projection_dim (`int`, *optional*, defaults to 512):
             Dimensionality of text and vision projection layers.
         logit_scale_init_value (`float`, *optional*, defaults to 2.6592):
-            The inital value of the *logit_scale* parameter. Default is used as per the original OWLv2
+            The initial value of the *logit_scale* parameter. Default is used as per the original OWLv2
             implementation.
         return_dict (`bool`, *optional*, defaults to `True`):
             Whether or not the model should return a dictionary. If `False`, returns a tuple.

src/transformers/models/owlvit/configuration_owlvit.py

@@ -59,7 +59,7 @@ class OwlViTTextConfig(PretrainedConfig):
             just in case (e.g., 512 or 1024 or 2048).
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         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):
@@ -171,7 +171,7 @@ class OwlViTVisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         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):
@@ -267,7 +267,7 @@ class OwlViTConfig(PretrainedConfig):
         projection_dim (`int`, *optional*, defaults to 512):
             Dimensionality of text and vision projection layers.
         logit_scale_init_value (`float`, *optional*, defaults to 2.6592):
-            The inital value of the *logit_scale* parameter. Default is used as per the original OWL-ViT
+            The initial value of the *logit_scale* parameter. Default is used as per the original OWL-ViT
             implementation.
         return_dict (`bool`, *optional*, defaults to `True`):
             Whether or not the model should return a dictionary. If `False`, returns a tuple.

src/transformers/models/pix2struct/configuration_pix2struct.py

@@ -189,7 +189,7 @@ class Pix2StructVisionConfig(PretrainedConfig):
             Number of attention heads for each attention layer in the Transformer encoder.
         dense_act_fn (`str` or `function`, *optional*, defaults to `"gelu_new"`):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
-            `"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported.
+            `"relu"`, `"selu"` and `"gelu_new"` `"gelu"` are supported.
         layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
         dropout_rate (`float`, *optional*, defaults to 0.0):

src/transformers/models/siglip/configuration_siglip.py

@@ -156,7 +156,7 @@ class SiglipVisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         hidden_act (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`):
             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.
+            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
         attention_dropout (`float`, *optional*, defaults to 0.0):