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

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

src/transformers/models/siglip/modeling_siglip.py

@@ -95,7 +95,7 @@ def trunc_normal_tf_(
 
     NOTE: this 'tf' variant behaves closer to Tensorflow / JAX impl where the
     bounds [a, b] are applied when sampling the normal distribution with mean=0, std=1.0
-    and the result is subsquently scaled and shifted by the mean and std args.
+    and the result is subsequently scaled and shifted by the mean and std args.
 
     Args:
         tensor: an n-dimensional `torch.Tensor`

src/transformers/models/tvp/configuration_tvp.py

@@ -89,7 +89,7 @@ class TvpConfig(PretrainedConfig):
             The dropout probability of hidden layers.
         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-12):
             The epsilon used by the layer normalization layers.
         initializer_range (`float`, *optional*, defaults to 0.02):

src/transformers/models/vision_text_dual_encoder/configuration_vision_text_dual_encoder.py

@@ -42,9 +42,9 @@ class VisionTextDualEncoderConfig(PretrainedConfig):
 
     Args:
         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.
 

src/transformers/models/x_clip/configuration_x_clip.py

@@ -52,7 +52,7 @@ class XCLIPTextConfig(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):
@@ -166,7 +166,7 @@ class XCLIPVisionConfig(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"`, `"gelu_new"` and ``"quick_gelu"` are supported.
+            `"relu"`, `"selu"`, `"gelu_new"` and `"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):
@@ -274,14 +274,14 @@ class XCLIPConfig(PretrainedConfig):
         vision_config (`dict`, *optional*):
             Dictionary of configuration options used to initialize [`XCLIPVisionConfig`].
         projection_dim (`int`, *optional*, defaults to 512):
-            Dimentionality of text and vision projection layers.
+            Dimensionality of text and vision projection layers.
         prompt_layers (`int`, *optional*, defaults to 2):
             Number of layers in the video specific prompt generator.
         prompt_alpha (`float`, *optional*, defaults to 0.1):
             Alpha value to use in the video specific prompt generator.
         prompt_hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`):
             The non-linear activation function (function or string) in the video specific prompt generator. If string,
-            `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` ``"quick_gelu"` are supported.
+            `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
         prompt_num_attention_heads (`int`, *optional*, defaults to 8):
             Number of attention heads in the cross-attention of the video specific prompt generator.
         prompt_attention_dropout (`float`, *optional*, defaults to 0.0):
@@ -341,7 +341,7 @@ class XCLIPConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`text_config_dict` is provided which will be used to initialize `XCLIPTextConfig`. The "
-                            f'value `text_config["{key}"]` will be overriden.'
+                            f'value `text_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)
 
@@ -373,7 +373,7 @@ class XCLIPConfig(PretrainedConfig):
                     else:
                         message = (
                             f"`vision_config_dict` is provided which will be used to initialize `XCLIPVisionConfig`. "
-                            f'The value `vision_config["{key}"]` will be overriden.'
+                            f'The value `vision_config["{key}"]` will be overridden.'
                         )
                     logger.info(message)