[docstring] Fix docstrings for `CLIP` (#26691)

fix docstrings for vanilla clip

src/transformers/models/clip/configuration_clip.py

@@ -168,10 +168,14 @@ class CLIPVisionConfig(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):
@@ -179,13 +183,13 @@ class CLIPVisionConfig(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/clip/tokenization_clip.py

@@ -284,13 +284,15 @@ class CLIPTokenizer(PreTrainedTokenizer):
         errors (`str`, *optional*, defaults to `"replace"`):
             Paradigm to follow when decoding bytes to UTF-8. See
             [bytes.decode](https://docs.python.org/3/library/stdtypes.html#bytes.decode) for more information.
-        unk_token (`str`, *optional*, defaults to `<|endoftext|>`):
+        unk_token (`str`, *optional*, defaults to `"<|endoftext|>"`):
             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 `<|startoftext|>`):
+        bos_token (`str`, *optional*, defaults to `"<|startoftext|>"`):
             The beginning of sequence token.
-        eos_token (`str`, *optional*, defaults to `<|endoftext|>`):
+        eos_token (`str`, *optional*, defaults to `"<|endoftext|>"`):
             The end of sequence token.
+        pad_token (`str`, *optional*, defaults to `"<|endoftext|>"`):
+            The token used for padding, for example when batching sequences of different lengths.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES

src/transformers/models/clip/tokenization_clip_fast.py

@@ -56,17 +56,21 @@ class CLIPTokenizerFast(PreTrainedTokenizerFast):
     refer to this superclass for more information regarding those methods.
 
     Args:
-        vocab_file (`str`):
+        vocab_file (`str`, *optional*):
             Path to the vocabulary file.
-        merges_file (`str`):
+        merges_file (`str`, *optional*):
             Path to the merges file.
-        unk_token (`str`, *optional*, defaults to `<|endoftext|>`):
+        tokenizer_file (`str`, *optional*):
+            The path to a tokenizer file to use instead of the vocab file.
+        unk_token (`str`, *optional*, defaults to `"<|endoftext|>"`):
             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 `<|startoftext|>`):
+        bos_token (`str`, *optional*, defaults to `"<|startoftext|>"`):
             The beginning of sequence token.
-        eos_token (`str`, *optional*, defaults to `<|endoftext|>`):
+        eos_token (`str`, *optional*, defaults to `"<|endoftext|>"`):
             The end of sequence token.
+        pad_token (`str`, *optional*, defaults to `"<|endoftext|>"`):
+            The token used for padding, for example when batching sequences of different lengths.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES

utils/check_docstrings.py

@@ -118,9 +118,6 @@ OBJECTS_TO_IGNORE = [
     "BridgeTowerTextConfig",
     "BridgeTowerVisionConfig",
     "BrosModel",
-    "CLIPTokenizer",
-    "CLIPTokenizerFast",
-    "CLIPVisionConfig",
     "CamembertConfig",
     "CamembertModel",
     "CamembertTokenizerFast",