o Zh/@sbdZddlmZddlmZeeZGdddeZGdddeZ Gdd d eZ gd Z d S) zSiglip model configuration)PretrainedConfig)loggingcsDeZdZdZdZdZ        dfdd ZZS)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 ```Zsiglip_text_model text_config} @gelu_pytorch_tanhư>Nc sltjd| | | d|||_||_||_||_||_||_||_||_ | |_ | dur1| |_ dS||_ dS)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)selfrrrrrrrrrrrrr kwargs __class__r^/var/www/auris/lib/python3.10/site-packages/transformers/models/siglip/configuration_siglip.pyrSszSiglipTextConfig.__init__) rrrr r r r r r rrrN__name__ __module__ __qualname____doc__ model_typeZbase_config_keyr __classcell__rrr#r%rs$7rcs>eZdZdZdZdZ       dfd d ZZS)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 ```Zsiglip_vision_model vision_configrrr rr r r c  sRtjdi| ||_||_||_||_||_||_||_| |_ | |_ ||_ dS)Nr) rrrrrr num_channels patch_size image_sizerrr) r!rrrrr1r3r2rrrr"r#rr%rs zSiglipVisionConfig.__init__) rrr r rr/r0r r r r&rrr#r%r-ts/r-csFeZdZdZdZeedZd fdd Ze dedefd d Z Z 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) ```Zsigliprr.Nc shtjdi||duri}td|duri}tdtdi||_tdi||_d|_dS)NzQ`text_config` is `None`. Initializing the `SiglipTextConfig` with default values.zU`vision_config` is `None`. initializing the `SiglipVisionConfig` with default values.g?r) rrloggerinforrr-r.Zinitializer_factor)r!rr.r"r#rr%rs   zSiglipConfig.__init__rr.cKs|d||d|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 r5Nr)to_dict)clsrr.r"rrr%from_text_vision_configss z%SiglipConfig.from_text_vision_configs)NN) r'r(r)r*r+rr-Z sub_configsr classmethodr:r,rrr#r%r4s) r4)r4rr-N) r*Zconfiguration_utilsrutilsrZ get_loggerr'r6rr-r4__all__rrrr%s   \O J