Ig dZddlZddlmZmZmZddlmZddlm Z e je Z GddeZ Gd d eZGd d eZGd deZGddeZy)zFLAVA model configurationsN)AnyDictUnion)PretrainedConfig)loggingceZdZdZdZ ddedededededed ed ed ed ed ededededeffd Ze de e e jfddfdZxZS)FlavaImageConfiga This is the configuration class to store the configuration of a [`FlavaImageModel`]. It is used to instantiate an FLAVA 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 FLAVA [facebook/flava-full](https://huggingface.co/facebook/flava-full) 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. mask_token (`bool`, *optional*, defaults to `True`): Whether to use a mask token or not. Used in MIM (Masked Image Modeling) loss for FLAVA. vocab_size (`int`, *optional*, defaults to 8192): Vocabulary size of the [`FlavaImageCodebook`] used in conjunction with [`FlavaImageModel`] for MIM (Masked Image Modeling) loss for FLAVA. Example: ```python >>> from transformers import FlavaImageConfig, FlavaImageModel >>> # Initializing a FlavaImageModel with style configuration >>> configuration = FlavaImageConfig() >>> # Initializing a FlavaImageModel model (with random weights) from the style configuration >>> model = FlavaImageModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```flava_image_model hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps image_size patch_size num_channelsqkv_bias mask_token vocab_sizec t|di|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_yN)super__init__r r rrrrrrrrrrrrr)selfr r rrrrrrrrrrrrrkwargs __class__s j/var/www/html/answerous/venv/lib/python3.12/site-packages/transformers/models/flava/configuration_flava.pyrzFlavaImageConfig.__init__Zs& "6"&!2#6 !2$#6 ,H)!2,$$(  $$pretrained_model_name_or_pathreturnrc >|j||j|fi|\}}|jddk(r|d}d|vrGt|dr;|d|jk7r)t j d|dd|jd|j|fi|S)N model_typeflava image_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors._set_token_in_kwargsget_config_dictgethasattrr(loggerwarning from_dictclsr%r! config_dicts r#from_pretrainedz FlavaImageConfig.from_pretraineds   (1c112OZSYZ V ??< (G 3%n5K ; &73 +E+VbJcgjguguJu NN0\1J0KKk>>""pr  s}}[3F33r$) r; gelur>{Gz?-q=rTT __name__ __module__ __qualname____doc__r(intfloatboolr classmethodrstrosPathLiker9 __classcell__r"s@r#r r s : x%J!##%!% %(.1#' %!#%#%#%! #%  #%  #%##%',#%!#%#%#%#%#%#%#% !#%J4E#r{{BR