qipdZddlmZddlmZddlmZmZeje Z GddeZ dgZ y) zPaliGemmamodel configuration)PreTrainedConfig)logging)CONFIG_MAPPING AutoConfigcZeZdZdZdZddiZeedZdgZ d de dzffd Z xZ 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. tie_word_embeddings (`bool`, *optional*, defaults to `True`): Whether to tie weight embeddings 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 ``` paligemmaimage_token_idimage_token_index) text_config vision_configpast_key_valuesNtie_word_embeddingsc ||_||_||_||_||_d|_t |jtr,|jdd|d<t|ddi||_n|tddddddd d d |_||_ t |jtr,|jdd |d<t|ddi||_ n|td d ddddd||_ |jjd|j_ |jj|jjzdz|j_||j_t |@di|y)NF model_typesiglip_vision_modelii)intermediate_size hidden_size patch_size image_sizenum_hidden_layersnum_attention_heads vocab_sizevision_use_headgemmai@)rrrrnum_key_value_headsis_encoder_decoderrTr)r projection_dimrrrr' isinstancedictgetrr use_bidirectional_attentionrrnum_image_tokenssuper__init__) selfrr r rr)rrkwargs __class__s g/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/paligemma/configuration_paligemma.pyr0zPaliGemmaConfig.__init__Os"3,&*#6 "' d(($ /*7*;*;LJ_*`M, '!/ l0K!L!]}!]D   "!/0E!F"& "$$&! % "D ' d&& -(3 g(NK %-k,.GHW;WD   -g6 "$"'$%$%#(% D     7 7 ?;?D   8-1-?-?-J-JdN`N`NkNk-kpq,q),:) "6")NNirr"r"T) __name__ __module__ __qualname____doc__r attribute_mapr sub_configskeys_to_ignore_at_inferenceboolr0 __classcell__)r3s@r4r r sa. `J-M#-zJK#4"5 +/7#"D[7#7#r5r N) r9configuration_utilsrutilsrautorr get_loggerr6loggerr __all__r(r5r4rEsA#3-   H %o#&o#d  r5