a hE@s*dZddlmZGdddeZdgZdS)zI-JEPA model configuration)PretrainedConfigcs&eZdZdZdZdfdd ZZS) IJepaConfiga# This is the configuration class to store the configuration of a [`IJepaModel`]. It is used to instantiate an IJEPA 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 I-JEPA [facebook/ijepa_vith14_1k](https://huggingface.co/facebook/ijepa_vith14_1k) 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. 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. Keys of ACT2FN are supported for Flax and Pytorch, and elements of https://www.tensorflow.org/api_docs/python/tf/keras/activations are supported for Tensorflow. Example: ```python >>> from transformers import IJepaConfig, IJepaModel >>> # Initializing a IJEPA ijepa-base-patch16-224 style configuration >>> configuration = IJepaConfig() >>> # Initializing a model (with random weights) from the ijepa-base-patch16-224 style configuration >>> model = IJepaModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zijepa gelu{Gz?-q=rTNtanhc sxtjfi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_|rh|n||_||_dS)N)super__init__ hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps image_size patch_size num_channelsqkv_biaspooler_output_size pooler_act)selfrrrrrrrrrrrrrrrkwargs __class__i/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/ijepa/configuration_ijepa.pyrSs zIJepaConfig.__init__)rrrrrrrr r r r rTNr )__name__ __module__ __qualname____doc__Z model_typer __classcell__r#r#r!r$rs$<rN)r(Zconfiguration_utilsrr__all__r#r#r#r$s e