[docstring] Fix docstring CLIP configs (#26677)

* fix docstrings for CLIP configs

* black formatted

src/transformers/models/clip/configuration_clip.py

@@ -54,6 +54,8 @@ class CLIPTextConfig(PretrainedConfig):
             Dimensionality of the encoder layers and the pooler layer.
         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.
         num_hidden_layers (`int`, *optional*, defaults to 12):
             Number of hidden layers in the Transformer encoder.
         num_attention_heads (`int`, *optional*, defaults to 8):
@@ -64,15 +66,21 @@ class CLIPTextConfig(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).
+        pad_token_id (`int`, *optional*, defaults to 1):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 49406):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 49407):
+            End of stream token id.
 
     Example:
 

src/transformers/models/clipseg/configuration_clipseg.py

@@ -56,15 +56,21 @@ class CLIPSegTextConfig(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).
+        pad_token_id (`int`, *optional*, defaults to 1):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 49406):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 49407):
+            End of stream token id.
 
     Example:
 
@@ -152,6 +158,8 @@ class CLIPSegVisionConfig(PretrainedConfig):
             Number of hidden layers in the Transformer encoder.
         num_attention_heads (`int`, *optional*, defaults to 12):
             Number of attention heads for each attention layer in the Transformer encoder.
+        num_channels (`int`, *optional*, defaults to 3):
+            The number of input channels.
         image_size (`int`, *optional*, defaults to 224):
             The size (resolution) of each image.
         patch_size (`int`, *optional*, defaults to 32):
@@ -159,13 +167,13 @@ class CLIPSegVisionConfig(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).
 

utils/check_docstrings.py

@@ -119,9 +119,6 @@ OBJECTS_TO_IGNORE = [
     "BridgeTowerVisionConfig",
     "BrosModel",
     "CLIPImageProcessor",
-    "CLIPSegTextConfig",
-    "CLIPSegVisionConfig",
-    "CLIPTextConfig",
     "CLIPTokenizer",
     "CLIPTokenizerFast",
     "CLIPVisionConfig",