o ZhR@sPdZddlmZddlmZddlmZmZee Z GdddeZ dgZ dS) zPaliGemmamodel configuration)PretrainedConfig)logging)CONFIG_MAPPING AutoConfigcsJeZdZdZdZddiZeedZdgZ    d fd d Z Z S)PaliGemmaConfiga This is the configuration class to store the configuration of a [`PaliGemmaForConditionalGeneration`]. It is used to instantiate an PaliGemmamodel according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the PaliGemma-2B. e.g. [paligemma-hf/paligemma-2b](https://huggingface.co/paligemma-hf/paligemma-2b) Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vision_config (`PaliGemmaVisionConfig`, *optional*): Custom vision config or dict text_config (`Union[AutoConfig, dict]`, *optional*): The config object of the text backbone. Can be any of `LlamaConfig` or `MistralConfig`. image_token_index (`int`, *optional*, defaults to 256000): The image token index to encode the image prompt. vocab_size (`int`, *optional*, defaults to 257152): Vocabulary size of the PaliGemmamodel. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`~PaliGemmaForConditionalGeneration`] projection_dim (`int`, *optional*, defaults to 2048): Dimension of the multimodal projection space. hidden_size (`int`, *optional*, defaults to 2048): Dimension of the hidden layer of the Language model. Example: ```python >>> from transformers import PaliGemmaForConditionalGeneration, PaliGemmaConfig, SiglipVisionConfig, GemmaConfig >>> # Initializing a Siglip-like vision config >>> vision_config = SiglipVisionConfig() >>> # Initializing a PaliGemma config >>> text_config = GemmaConfig() >>> # Initializing a PaliGemma paligemma-3b-224 style configuration >>> configuration = PaliGemmaConfig(vision_config, text_config) >>> # Initializing a model from the paligemma-3b-224 style configuration >>> model = PaliGemmaForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Z paligemmaZimage_token_idimage_token_index) text_config vision_configZpast_key_valuesNc s ||_||_||_||_d|_t|jtr.d|vr|dnd|d<t|ddi||_n|durAtddddddd d dd |_||_t|jtrcd|vrR|dnd |d<t|ddi||_n|durutd d ddddd|d|_|jj |jj d|j_ ||j_t j di|dS)NF model_typeZsiglip_vision_modeliir )intermediate_size hidden_size patch_size image_sizenum_hidden_layersnum_attention_heads vocab_sizeZvision_use_headZgemmar i@)rrrrZnum_key_value_headsis_encoder_decoderrr)rprojection_dimrr r isinstancedictrr rrZnum_image_tokenssuper__init__)selfr r rrrrkwargs __class__rd/var/www/auris/lib/python3.10/site-packages/transformers/models/paligemma/configuration_paligemma.pyr#NsJ    zPaliGemmaConfig.__init__)NNr r r r ) __name__ __module__ __qualname____doc__rZ attribute_maprZ sub_configsZkeys_to_ignore_at_inferencer# __classcell__rrr&r(rs. rN) r,Zconfiguration_utilsrutilsrautorrZ get_loggerr)loggerr__all__rrrr(s    j