Ig+ddlZddlmZddlmZddlmZejeZ GddeZ Gdd eZ y) N)Union)PretrainedConfig)loggingcveZdZdZdZ dfd Zedeee jfddfdZ xZ S) GitVisionConfiga This is the configuration class to store the configuration of a [`GitVisionModel`]. It is used to instantiate a GIT 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 GIT [microsoft/git-base](https://huggingface.co/microsoft/git-base) 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. 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. 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. hidden_act (`str` or `function`, *optional*, defaults to `"quick_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-5): 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. Example: ```python >>> from transformers import GitVisionConfig, GitVisionModel >>> # Initializing a GitVisionConfig with microsoft/git-base style configuration >>> configuration = GitVisionConfig() >>> # Initializing a GitVisionModel (with random weights) from the microsoft/git-base style configuration >>> model = GitVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```git_vision_modelc  t |di| ||_||_||_||_||_||_||_| |_ | |_ | |_ ||_ y)N) super__init__ hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads num_channels patch_size image_sizeinitializer_rangeattention_dropoutlayer_norm_eps hidden_act)selfrrrrrrrrrrrkwargs __class__s f/var/www/html/answerous/venv/lib/python3.12/site-packages/transformers/models/git/configuration_git.pyr zGitVisionConfig.__init__Lsj "6"&!2!2#6 ($$!2!2,$pretrained_model_name_or_pathreturnrc >|j||j|fi|\}}|jddk(r|d}d|vrGt|dr;|d|jk7r)t j d|dd|jd|j|fi|S)N model_typegit vision_configzYou are using a model of type z to instantiate a model of type zN. This is not supported for all configurations of models and can yield errors.)_set_token_in_kwargsget_config_dictgethasattrr!loggerwarning from_dict)clsrr config_dicts rfrom_pretrainedzGitVisionConfig.from_pretrainedis   (1c112OZSYZ V ??< (E 1%o6K ; &73 +E+VbJcgjguguJu NN0\1J0KKk>>""pr  s}}[3F33r)  r0r quick_gelugh㈵>g{Gz?) __name__ __module__ __qualname____doc__r!r classmethodrstrosPathLiker- __classcell__rs@rrrsi- ^$J%:4E#r{{BR