qi`dZddlmZddlmZej eZGddeZdgZ y)zViT model configuration)PreTrainedConfig)loggingcHeZdZdZdZ dfd ZxZS) ViTConfiga This is the configuration class to store the configuration of a [`ViTModel`]. It is used to instantiate an ViT 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 ViT [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: 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 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 16): 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. encoder_stride (`int`, *optional*, defaults to 16): Factor to increase the spatial resolution by in the decoder head for masked image modeling. pooler_output_size (`int`, *optional*): Dimensionality of the pooler layer. If None, defaults to `hidden_size`. pooler_act (`str`, *optional*, defaults to `"tanh"`): The activation function to be used by the pooler. Example: ```python >>> from transformers import ViTConfig, ViTModel >>> # Initializing a ViT vit-base-patch16-224 style configuration >>> configuration = ViTConfig() >>> # Initializing a model (with random weights) from the vit-base-patch16-224 style configuration >>> model = ViTModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```vitc ||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ |r|n||_||_t!|Ddi|y)N) hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps image_size patch_size num_channelsqkv_biasencoder_stridepooler_output_size pooler_actsuper__init__)selfr r r r rrrrrrrrrrrrkwargs __class__s [/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/vit/configuration_vit.pyrzViTConfig.__init__Vs('!2#6 !2$#6 ,H)!2,$$(  ,8J"4P[$ "6")i r!i gelur#g{Gz?g-q=rTr%Ntanh)__name__ __module__ __qualname____doc__ model_typer __classcell__)rs@rrrsL: xJ%(#%#%#r rN) r*configuration_utilsrutilsr get_loggerr'loggerr__all__r r rr2s=3   H %d# d#N -r