o ¹ÈÏi­ã@s&ddlmZGdd„deƒZdgZdS)é)ÚPretrainedConfigcsDeZdZdZdZdZ        d‡fdd„ Z‡ZS)ÚMLCDVisionConfiga This is the configuration class to store the configuration of a [`MLCDVisionModel`]. It is used to instantiate a MLCD vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the vision encoder of the MLCD [DeepGlint-AI/mlcd-vit-bigG-patch14-336](https://huggingface.co/DeepGlint-AI/mlcd-vit-bigG-patch14-336) 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 1664): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 8192): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. projection_dim (`int`, *optional*, defaults to 1024): Dimensionality of text and vision projection layers. num_hidden_layers (`int`, *optional*, defaults to 48): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): 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 336): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 14): The size (resolution) of each patch. 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"` `"quick_gelu"` are supported. 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 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). Example: ```python >>> from transformers import MLCDVisionConfig, MLCDVisionModel >>> # Initializing a MLCDVisionConfig with DeepGlint-AI/mlcd-vit-bigG-patch14-336 style configuration >>> configuration = MLCDVisionConfig() >>> # Initializing a MLCDVisionModel (with random weights) from the DeepGlint-AI/mlcd-vit-bigG-patch14-336 style configuration >>> model = MLCDVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Úmlcd_vision_modelÚ vision_configé€é é0ééréPéÚgeluçñh㈵øä>çç{®Gáz”?çð?c sdtƒjdi|¤Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_dS)N©)ÚsuperÚ__init__Ú hidden_sizeÚintermediate_sizeÚnum_hidden_layersÚnum_attention_headsÚnum_key_value_groupsÚ num_channelsÚ patch_sizeÚ image_sizeÚinitializer_rangeÚinitializer_factorÚattention_dropoutÚlayer_norm_epsÚ hidden_act)Úselfrrrrrrrrr!r rrrÚkwargs©Ú __class__rú_/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/mlcd/configuration_mlcd.pyrSs zMLCDVisionConfig.__init__) rrrr r rr r r rrrr)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚbase_config_keyrÚ __classcell__rrr$r&rs$6òrN)Úconfiguration_utilsrrÚ__all__rrrr&Ús  \