sgd.dZddlmZddlmZej eZGddeZGddeZ Gdd eZ y ) zSiglip model configuration)PretrainedConfig)loggingcDeZdZdZdZdZ dfd ZxZS)SiglipTextConfiga6 This is the configuration class to store the configuration of a [`SiglipTextModel`]. It is used to instantiate a Siglip text 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 text encoder of the Siglip [google/siglip-base-patch16-224](https://huggingface.co/google/siglip-base-patch16-224) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 32000): Vocabulary size of the Siglip text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`SiglipModel`]. 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. max_position_embeddings (`int`, *optional*, defaults to 64): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). 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. pad_token_id (`int`, *optional*, defaults to 1): The id of the padding token in the vocabulary. bos_token_id (`int`, *optional*, defaults to 49406): The id of the beginning-of-sequence token in the vocabulary. eos_token_id (`int`, *optional*, defaults to 49407): The id of the end-of-sequence token in the vocabulary. Example: ```python >>> from transformers import SiglipTextConfig, SiglipTextModel >>> # Initializing a SiglipTextConfig with google/siglip-base-patch16-224 style configuration >>> configuration = SiglipTextConfig() >>> # Initializing a SiglipTextModel (with random weights) from the google/siglip-base-patch16-224 style configuration >>> model = SiglipTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```siglip_text_model text_configc  t|d| | | d| ||_||_||_||_||_||_||_||_ | |_ y)N) pad_token_id bos_token_id eos_token_id) super__init__ vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsmax_position_embeddingslayer_norm_eps hidden_actattention_dropout)selfrrrrrrrrrr r r kwargs __class__s b/var/www/html/venv/lib/python3.12/site-packages/transformers/models/siglip/configuration_siglip.pyrzSiglipTextConfig.__init__Qsf$ sl\hslrs$&!2!2#6 '>$,$!2) i} r @gelu_pytorch_tanhư>ii__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__rs@rrrsG3 j%J#O "&33rrc@eZdZdZdZdZ dfd ZxZS)SiglipVisionConfiga' This is the configuration class to store the configuration of a [`SiglipVisionModel`]. It is used to instantiate a Siglip 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 Siglip [google/siglip-base-patch16-224](https://huggingface.co/google/siglip-base-patch16-224) 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. 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 16): 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. Example: ```python >>> from transformers import SiglipVisionConfig, SiglipVisionModel >>> # Initializing a SiglipVisionConfig with google/siglip-base-patch16-224 style configuration >>> configuration = SiglipVisionConfig() >>> # Initializing a SiglipVisionModel (with random weights) from the google/siglip-base-patch16-224 style configuration >>> model = SiglipVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```siglip_vision_model vision_configc  t |di| ||_||_||_||_||_||_||_| |_ | |_ ||_ y)Nr ) rrrrrr num_channels patch_size image_sizerrr) rrrrrr4r6r5rrrrrs rrzSiglipVisionConfig.__init__sb "6"&!2!2#6 ($$!2,$r) rrr r rr"r#r$r&r.s@rr0r0ps?- ^'J%O&%%rr0cLeZdZdZdZeedZdfd Ze dedefdZ xZ S) SiglipConfigaC [`SiglipConfig`] is the configuration class to store the configuration of a [`SiglipModel`]. It is used to instantiate a Siglip model according to the specified arguments, defining the text model and vision model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the Siglip [google/siglip-base-patch16-224](https://huggingface.co/google/siglip-base-patch16-224) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`SiglipTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`SiglipVisionConfig`]. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import SiglipConfig, SiglipModel >>> # Initializing a SiglipConfig with google/siglip-base-patch16-224 style configuration >>> configuration = SiglipConfig() >>> # Initializing a SiglipModel (with random weights) from the google/siglip-base-patch16-224 style configuration >>> model = SiglipModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a SiglipConfig from a SiglipTextConfig and a SiglipVisionConfig >>> from transformers import SiglipTextConfig, SiglipVisionConfig >>> # Initializing a SiglipText and SiglipVision configuration >>> config_text = SiglipTextConfig() >>> config_vision = SiglipVisionConfig() >>> config = SiglipConfig.from_text_vision_configs(config_text, config_vision) ```sigliprr2c t|di||i}tjd|i}tjdt di||_t di||_d|_y)NzQ`text_config` is `None`. Initializing the `SiglipTextConfig` with default values.zU`vision_config` is `None`. initializing the `SiglipVisionConfig` with default values.g?r ) rrloggerinforrr0r2initializer_factor)rrr2rrs rrzSiglipConfig.__init__sk "6"  K KKk l  M KKo p+:k:/@-@"%rrr2c P|d|j|jd|S)z Instantiate a [`SiglipConfig`] (or a derived class) from siglip text model configuration and siglip vision model configuration. Returns: [`SiglipConfig`]: An instance of a configuration object r<r )to_dict)clsrr2rs rfrom_text_vision_configsz%SiglipConfig.from_text_vision_configss,f{224MDYDYD[f_effr)NN) r'r(r)r*r+rr0 sub_configsr classmethodrDr-r.s@rr:r:sH' RJ"2EWXK&  g3C gTf g grr:N) r*configuration_utilsrutilsr get_loggerr'r>rr0r:r rrrJsU!3   H %U3'U3pL%)L%^Gg#Ggr