[docstring] Fix docstring for AltCLIPTextConfig, AltCLIPVisionConfig and AltCLIPConfig (#27128)

* [docstring] Fix docstring for AltCLIPVisionConfig, AltCLIPTextConfig + cleaned some docstring

* Removed entries from check_docstring.py

* Removed entries from check_docstring.py

* Removed entry from check_docstring.py

* [docstring] Fix docstring for AltCLIPTextConfig, AltCLIPVisionConfig and AltCLIPConfig

src/transformers/models/altclip/configuration_altclip.py

@@ -61,12 +61,19 @@ class AltCLIPTextConfig(PretrainedConfig):
         max_position_embeddings (`int`, *optional*, defaults to 514):
             The maximum sequence length that this model might ever be used with. Typically set this to something large
             just in case (e.g., 512 or 1024 or 2048).
-        type_vocab_size (`int`, *optional*, defaults to 2):
+        type_vocab_size (`int`, *optional*, defaults to 1):
             The vocabulary size of the `token_type_ids` passed when calling [`AltCLIPTextModel`]
         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):
+        initializer_factor (`float`, *optional*, defaults to 0.02):
+            A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
+            testing).
+        layer_norm_eps (`float`, *optional*, defaults to 1e-05):
             The epsilon used by the layer normalization layers.
+        pad_token_id (`int`, *optional*, defaults to 1): The id of the *padding* token.
+        bos_token_id (`int`, *optional*, defaults to 0): The id of the *beginning-of-sequence* token.
+        eos_token_id (`Union[int, List[int]]`, *optional*, defaults to 2):
+            The id of the *end-of-sequence* token. Optionally, use a list to set multiple *end-of-sequence* tokens.
         position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
             Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
             positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
@@ -154,10 +161,14 @@ class AltCLIPVisionConfig(PretrainedConfig):
             Dimensionality of the encoder layers and the pooler layer.
         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.
         num_hidden_layers (`int`, *optional*, defaults to 12):
             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):
@@ -165,13 +176,13 @@ class AltCLIPVisionConfig(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/bridgetower/configuration_bridgetower.py

@@ -49,7 +49,7 @@ class BridgeTowerVisionConfig(PretrainedConfig):
             The size (resolution) of each patch.
         image_size (`int`, *optional*, defaults to 288):
             The size (resolution) of each image.
-        initializer_factor (`float``, *optional*, defaults to 1):
+        initializer_factor (`float`, *optional*, defaults to 1):
             A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
             testing).
         layer_norm_eps (`float`, *optional*, defaults to 1e-05):
@@ -151,7 +151,7 @@ class BridgeTowerTextConfig(PretrainedConfig):
             just in case (e.g., 512 or 1024 or 2048).
         type_vocab_size (`int`, *optional*, defaults to 2):
             The vocabulary size of the `token_type_ids`.
-        initializer_factor (`float``, *optional*, defaults to 1):
+        initializer_factor (`float`, *optional*, defaults to 1):
             A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
             testing).
         layer_norm_eps (`float`, *optional*, defaults to 1e-05):
@@ -255,7 +255,7 @@ class BridgeTowerConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler.
         hidden_size (`int`, *optional*, defaults to 768):
             Dimensionality of the encoder layers and the pooler layer.
-        initializer_factor (`float``, *optional*, defaults to 1):
+        initializer_factor (`float`, *optional*, defaults to 1):
             A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
             testing).
         layer_norm_eps (`float`, *optional*, defaults to 1e-05):

src/transformers/models/chinese_clip/configuration_chinese_clip.py

@@ -203,7 +203,7 @@ class ChineseCLIPVisionConfig(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.
-        initializer_factor (`float``, *optional*, defaults to 1.0):
+        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).
     Example:

src/transformers/models/clipseg/configuration_clipseg.py

@@ -62,7 +62,7 @@ class CLIPSegTextConfig(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.
-        initializer_factor (`float``, *optional*, defaults to 1.0):
+        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):

src/transformers/models/mask2former/configuration_mask2former.py

@@ -93,7 +93,7 @@ class Mask2FormerConfig(PretrainedConfig):
             Ratio of points that are sampled via importance sampling.
         init_std (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        init_xavier_std (`float``, *optional*, defaults to 1.0):
+        init_xavier_std (`float`, *optional*, defaults to 1.0):
             The scaling factor used for the Xavier initialization gain in the HM Attention map module.
         use_auxiliary_loss (`boolean``, *optional*, defaults to `True`):
             If `True` [`Mask2FormerForUniversalSegmentationOutput`] will contain the auxiliary losses computed using

src/transformers/models/owlv2/configuration_owlv2.py

@@ -180,7 +180,7 @@ class Owlv2VisionConfig(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.
-        initializer_factor (`float``, *optional*, defaults to 1.0):
+        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/configuration_owlvit.py

@@ -183,7 +183,7 @@ class OwlViTVisionConfig(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.
-        initializer_factor (`float``, *optional*, defaults to 1.0):
+        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/pix2struct/configuration_pix2struct.py

@@ -203,7 +203,7 @@ class Pix2StructVisionConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 1e-10):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        initializer_factor (`float``, *optional*, defaults to 1.0):
+        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).
         seq_len (`int`, *optional*, defaults to 4096):

src/transformers/models/x_clip/configuration_x_clip.py

@@ -63,7 +63,7 @@ class XCLIPTextConfig(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.
-        initializer_factor (`float``, *optional*, defaults to 1):
+        initializer_factor (`float`, *optional*, defaults to 1):
             A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
             testing).
 
@@ -176,7 +176,7 @@ class XCLIPVisionConfig(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.
-        initializer_factor (`float``, *optional*, defaults to 1):
+        initializer_factor (`float`, *optional*, defaults to 1):
             A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
             testing).
         drop_path_rate (`float`, *optional*, defaults to 0.0):

utils/check_docstrings.py

@@ -79,8 +79,6 @@ OBJECTS_TO_IGNORE = [
     "AlbertTokenizerFast",
     "AlignTextModel",
     "AlignVisionConfig",
-    "AltCLIPTextConfig",
-    "AltCLIPVisionConfig",
     "AudioClassificationPipeline",
     "AutoformerConfig",
     "AutomaticSpeechRecognitionPipeline",