qi `dZddlmZddlmZej eZGddeZdgZ y)zLeViT model configuration)PreTrainedConfig)loggingc\eZdZdZdZddddddgdgd gd gd d gd gd dffd ZxZS) LevitConfiga This is the configuration class to store the configuration of a [`LevitModel`]. It is used to instantiate a LeViT 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 LeViT [facebook/levit-128S](https://huggingface.co/facebook/levit-128S) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: image_size (`int`, *optional*, defaults to 224): The size of the input image. num_channels (`int`, *optional*, defaults to 3): Number of channels in the input image. kernel_size (`int`, *optional*, defaults to 3): The kernel size for the initial convolution layers of patch embedding. stride (`int`, *optional*, defaults to 2): The stride size for the initial convolution layers of patch embedding. padding (`int`, *optional*, defaults to 1): The padding size for the initial convolution layers of patch embedding. patch_size (`int`, *optional*, defaults to 16): The patch size for embeddings. hidden_sizes (`list[int]`, *optional*, defaults to `[128, 256, 384]`): Dimension of each of the encoder blocks. num_attention_heads (`list[int]`, *optional*, defaults to `[4, 8, 12]`): Number of attention heads for each attention layer in each block of the Transformer encoder. depths (`list[int]`, *optional*, defaults to `[4, 4, 4]`): The number of layers in each encoder block. key_dim (`list[int]`, *optional*, defaults to `[16, 16, 16]`): The size of key in each of the encoder blocks. drop_path_rate (`int`, *optional*, defaults to 0): The dropout probability for stochastic depths, used in the blocks of the Transformer encoder. mlp_ratios (`list[int]`, *optional*, defaults to `[2, 2, 2]`): Ratio of the size of the hidden layer compared to the size of the input layer of the Mix FFNs in the encoder blocks. attention_ratios (`list[int]`, *optional*, defaults to `[2, 2, 2]`): Ratio of the size of the output dimension compared to input dimension of attention layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Example: ```python >>> from transformers import LevitConfig, LevitModel >>> # Initializing a LeViT levit-128S style configuration >>> configuration = LevitConfig() >>> # Initializing a model (with random weights) from the levit-128S style configuration >>> model = LevitModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```levitr)i) )rrr)r r r )r r r g{Gz?c Bt|di|||_||_||_||_||_||_||_| |_ | |_ | |_ ||_ | |_ | |_||_d| d|d| dzdddgd| d|d| dzdddgg|_y)N Subsamplerrr r )super__init__ image_size num_channels kernel_sizestridepadding hidden_sizesnum_attention_headsdepthskey_dimdrop_path_rate patch_sizeattention_ratio mlp_ratioinitializer_rangedown_ops)selfrrrrrr!rrrrr r#r"r$kwargs __class__s _/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/levit/configuration_levit.pyrzLevitConfig.__init__Qs$ "6"$(&  (#6   ,$."!2 '!*l1o&CQ1 M '!*l1o&CQ1 M  )__name__ __module__ __qualname____doc__ model_typer __classcell__)r(s@r)rrsF5 nJ$&!$ $ r*rN) r.configuration_utilsrutilsr get_loggerr+loggerr__all__rr*r)r6s= 3   H %^ "^ B /r*