T^(h/dZddlmZddlmZej eZGddeZGddeZ Gdd eZ gd Z y ) zSiglip model configuration)PretrainedConfig)loggingcFeZdZdZdZdZ dfd ZxZS)SiglipTextConfiga 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. projection_size (`int`, *optional*, defaults to `hidden_size`): The size of the projection head. 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||_ 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_dropoutprojection_size)selfrrrrrrrrrr r r rkwargs __class__s m/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/siglip/configuration_siglip.pyrzSiglipTextConfig.__init__Ss{& sl\hslrs$&!2!2#6 '>$,$!22A2MS^) i} r!@gelu_pytorch_tanhư>iiN__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__rs@rrrsL5 n%J#O "&!__rrc@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) rrrrrr5r7r6rrrrrs rrzSiglipVisionConfig.__init__sb "6"&!2!2#6 ($$!2,$r) rr r!r!rr#r$r%r'r/s@rr1r1ts?- ^'J%O&%%rr1cLeZdZdZdZeedZdfd 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) ```sigliprr3c 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 ) rrloggerinforrr1r3initializer_factor)rrr3rrs rrzSiglipConfig.__init__sk "6"  K KKk l  M KKo p+:k:/@-@"%rrr3c 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)clsrr3rs rfrom_text_vision_configsz%SiglipConfig.from_text_vision_configss,f{224MDYDYD[f_effr)NN) r(r)r*r+r,rr1 sub_configsr classmethodrEr.r/s@rr;r;sH' RJ"2EWXK&  g3C gTf g grr;)r;rr1N) r+configuration_utilsrutilsr get_loggerr(r?rr1r;__all__r rrrLs`!3   H %Y_'Y_xL%)L%^Gg#GgT Er