fTh`SrSSKJr SSKJr \R "\5r"SS\5rS/r g)zVilT model configuration)PretrainedConfig)loggingc\^\rSrSrSrSrSU4SjjrSrU=r$) ViltConfiga This is the configuration class to store the configuration of a [`ViLTModel`]. It is used to instantiate an ViLT model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the ViLT [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 30522): Vocabulary size of the text part of the model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ViltModel`]. type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`ViltModel`]. This is used when encoding text. modality_type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the modalities passed when calling [`ViltModel`]. This is used after concatenating the embeddings of the text and image modalities. max_position_embeddings (`int`, *optional*, defaults to 40): The maximum sequence length that this model might ever be used with. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. 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. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. 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"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`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. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. image_size (`int`, *optional*, defaults to 384): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 32): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. max_image_length (`int`, *optional*, defaults to -1): The maximum number of patches to take as input for the Transformer encoder. If set to a positive integer, the encoder will sample `max_image_length` patches at maximum. If set to -1, will not be taken into account. num_images (`int`, *optional*, defaults to -1): The number of images to use for natural language visual reasoning. If set to a positive integer, will be used by [`ViltForImagesAndTextClassification`] for defining the classifier head. Example: ```python >>> from transformers import ViLTModel, ViLTConfig >>> # Initializing a ViLT dandelin/vilt-b32-mlm style configuration >>> configuration = ViLTConfig() >>> # Initializing a model from the dandelin/vilt-b32-mlm style configuration >>> model = ViLTModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```viltc >[TU]"SSU0UD6 XlX lX0lX@lXPlX`lXplXl Xl Xl Xl Xl XlXlXlUUlUUlUUlUUlg)Ntie_word_embeddings)super__init__ vocab_sizetype_vocab_sizemodality_type_vocab_sizemax_position_embeddings hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps image_size patch_size num_channelsqkv_biasmax_image_length num_images)selfrrrrrrrrrrrrrrrrrrr r kwargs __class__s c/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/vilt/configuration_vilt.pyr ViltConfig.__init__bs0 K-@KFK$.(@%'>$&!2#6 !2$#6 ,H)!2,$$(  0$)rrrrrrrrrrrrrrr rrrr)i:wr'(i r)i gelur+g{Gz?g-q=i rTFr-) __name__ __module__ __qualname____firstlineno____doc__ model_typer __static_attributes__ __classcell__)r#s@r$rrsYE NJ!" "%(!+.%.%r&rN) r2configuration_utilsrutilsr get_loggerr.loggerr__all__r r&r$r;s;3   H %x%!x%v .r&