`iddZddlmZddlmZejeZGddeZdgZ dS)zPixtral model configuration)PretrainedConfig)loggingc>eZdZdZdZ d fd ZxZS)PixtralVisionConfigaT This is the configuration class to store the configuration of a [`PixtralVisionModel`]. It is used to instantiate an Pixtral vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to the vision encoder used by Pixtral-12B. e.g. [pixtral-hf/pixtral-9b](https://huggingface.co/pixtral-hf/pixtral-9b) 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 1024): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 4096): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads in the Transformer encoder. num_channels (`int`, *optional*, defaults to 3): Number of input channels in the input images. image_size (`int`, *optional*, defaults to 1024): Max dimension of the input images. patch_size (`int`, *optional*, defaults to 16): Size of the image patches. hidden_act (`str`, *optional*, defaults to `"gelu"`): Activation function used in the hidden layers. attention_dropout (`float`, *optional*, defaults to 0.0): Dropout probability for the attention layers. rope_theta (`float`, *optional*, defaults to 10000.0): The base period of the RoPE embeddings. 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 PixtralVisionModel, PixtralVisionConfig >>> # Initializing a Pixtral-12B style configuration >>> config = PixtralVisionConfig() >>> # Initializing a model (with randomly initialized weights) from the configuration >>> model = PixtralVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```pixtralrgelu@{Gz?c  tjdi| ||_||_||_||_||_||_||_| |_ ||_ | |_ ||z|_ | |_ dS)N)super__init__ hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads num_channels patch_size image_sizeattention_dropout hidden_act rope_thetahead_diminitializer_range)selfrrrrrrrrrrrkwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/pixtral/configuration_pixtral.pyrzPixtralVisionConfig.__init__Ks ""6"""&!2!2#6 ($$!2$$#':: !2) rr r r rrr r r rr)__name__ __module__ __qualname____doc__ model_typer __classcell__)r"s@r#rrsr/ / bJ3333333333r$rN) r(configuration_utilsrutilsr get_loggerr%loggerr__all__rr$r#r0s"!333333  H % %P3P3P3P3P3*P3P3P3f ! !r$