% &h4ddlmZddlmZejeZGddeZGddeZGddeZ gd Z y ) )PretrainedConfig)loggingcFeZdZdZdZdZ dfd ZxZS)Siglip2TextConfiga This is the configuration class to store the configuration of a [`Siglip2TextModel`]. It is used to instantiate a Siglip2 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 Siglip2 [google/siglip2-base-patch16-224](https://huggingface.co/google/siglip2-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 Siglip2 text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Siglip2Model`]. 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 Siglip2TextConfig, Siglip2TextModel >>> # Initializing a Siglip2TextConfig with google/siglip2-base-patch16-224 style configuration >>> configuration = Siglip2TextConfig() >>> # Initializing a Siglip2TextModel (with random weights) from the google/siglip2-base-patch16-224 style configuration >>> model = Siglip2TextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```siglip2_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 /var/www/pru.catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/siglip2/configuration_siglip2.pyrzSiglip2TextConfig.__init__Xs{& 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)Siglip2VisionConfigaO This is the configuration class to store the configuration of a [`Siglip2VisionModel`]. It is used to instantiate a Siglip2 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 Siglip2 [google/siglip2-base-patch16-naflex](https://huggingface.co/google/siglip2-base-patch16-naflex) 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. num_patches (`int`, *optional*, defaults to 256): The number of patches in the image with the size of (`patch_size`, `patch_size`). The image is resized to fill maximum of this number of patches, and to preserve the aspect ratio. In case the resulted number of patches is lower, the image is padded in "patch" dimension. 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 Siglip2VisionConfig, Siglip2VisionModel >>> # Initializing a Siglip2VisionConfig with google/siglip2-base-patch16-naflex style configuration >>> configuration = Siglip2VisionConfig() >>> # Initializing a Siglip2VisionModel (with random weights) from the google/siglip2-base-patch16-naflex style configuration >>> model = Siglip2VisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```siglip2_vision_model vision_configc  t |di| ||_||_||_||_||_||_| |_| |_ ||_ ||_ y)Nr ) rrrrrr num_channels patch_sizerrr num_patches) rrrrrr5r7r6rrrrrs rrzSiglip2VisionConfig.__init__sc "6"&!2!2#6 ($!2,$&r) rr r!r!rr#r$r%r'r/s@rr1r1ys?0 d(J%O&''rr1cLeZdZdZdZeedZdfd Ze dedefdZ xZ S) Siglip2Configa] [`Siglip2Config`] is the configuration class to store the configuration of a [`Siglip2Model`]. It is used to instantiate a Siglip2 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 Siglip2 [google/siglip2-base-patch16-224](https://huggingface.co/google/siglip2-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 [`Siglip2TextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Siglip2VisionConfig`]. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import Siglip2Config, Siglip2Model >>> # Initializing a Siglip2Config with google/siglip2-base-patch16-224 style configuration >>> configuration = Siglip2Config() >>> # Initializing a Siglip2Model (with random weights) from the google/siglip2-base-patch16-224 style configuration >>> model = Siglip2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a Siglip2Config from a Siglip2TextConfig and a Siglip2VisionConfig >>> from transformers import Siglip2TextConfig, Siglip2VisionConfig >>> # Initializing a Siglip2Text and Siglip2Vision configuration >>> config_text = Siglip2TextConfig() >>> config_vision = Siglip2VisionConfig() >>> config = Siglip2Config.from_text_vision_configs(config_text, config_vision) ```siglip2rr3c t|di||i}tjd|i}tjdt di||_t di||_d|_y)NzR`text_config` is `None`. Initializing the `Siglip2TextConfig` with default values.zV`vision_config` is `None`. initializing the `Siglip2VisionConfig` with default values.g?r ) rrloggerinforrr1r3initializer_factor)rrr3rrs rrzSiglip2Config.__init__sk "6"  K KKl m  M KKp q,;{;0A=A"%rrr3c P|d|j|jd|S)z Instantiate a [`Siglip2Config`] (or a derived class) from siglip2 text model configuration and siglip2 vision model configuration. Returns: [`Siglip2Config`]: An instance of a configuration object r=r )to_dict)clsrr3rs rfrom_text_vision_configsz&Siglip2Config.from_text_vision_configss,f{224MDYDYD[f_effr)NN) r(r)r*r+r,rr1 sub_configsr classmethodrEr.r/s@rr;r;sH' RJ"3FYZK&  g3D gUh g grr;)r;rr1N) configuration_utilsrutilsr get_loggerr(r?rr1r;__all__r rrrLs],4   H %Y_(Y_xO'*O'dGg$GgT Hr