g1dZddlZddlmZddlmZddlmZddlm Z ej e Z Gd d eZ Gd d eZGd deZdS)zIdefics2 model configurationN)Union)PretrainedConfig)logging)CONFIG_MAPPINGcxeZdZdZdZ dfd Zedeee j fddfdZ xZ S)Idefics2VisionConfiga This is the configuration class to store the configuration of a [`Idefics2VisionModel`]. It is used to instantiate a Idefics2 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 SigLIP checkpoint [google/siglip-base-patch16-224](https://huggingface.co/google/siglip-base-patch16-224) used in the Idefics2 model [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b). 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. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. 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. num_channels (`int`, *optional*, defaults to 3): Number of channels in the input images. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 32): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`): 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-06): 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 for initializing all weight matrices in the model. Example: ```python >>> from transformers.models.idefics2.modeling_idefics2 import Idefics2VisionTransformer >>> from transformers.models.idefics2.configuration_idefics2 import Idefics2VisionConfig >>> # Initializing a Idefics2VisionConfig with google/siglip-base-patch16-224 style configuration >>> configuration = Idefics2VisionConfig() >>> # Initializing a Idefics2VisionTransformer (with random weights) from the google/siglip-base-patch16-224 style configuration >>> model = Idefics2VisionTransformer(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```idefics2 r gelu_pytorch_tanhư>{Gz?c  tjdi| ||_||_||_||_||_||_||_| |_ | |_ ||_ | |_ dS)N) super__init__ hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads num_channels patch_size image_sizeattention_dropoutlayer_norm_eps hidden_actinitializer_range)selfrrrrrrrr"r!r r#kwargs __class__s o/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/idefics2/configuration_idefics2.pyrzIdefics2VisionConfig.__init__Qs} ""6"""&!2!2#6 ($$!2,$!2pretrained_model_name_or_pathreturnrc N|||j|fi|\}}|ddkr|d}d|vrMt|dr=|d|jkr,t d|dd|jd|j|fi|S)N model_typer vision_configzYou are using a model of type z to instantiate a model of type zN. This is not supported for all configurations of models and can yield errors.)_set_token_in_kwargsget_config_dictgethasattrr,loggerwarning from_dict)clsr)r% config_dicts r'from_pretrainedz$Idefics2VisionConfig.from_pretrainedns   (((1c12OZZSYZZ V ??< ( (J 6 6%o6K ; & &73 +E+E &+VbJcgjguJuJu NNr\1Jrr>rrr    s}[33F333r() r r rrrrrrrrr) __name__ __module__ __qualname____doc__r,r classmethodrstrosPathLiker7 __classcell__r&s@r'r r s1 1 fJ&333333:4E#r{BR