g4dZddlZddlmZddlmZddlmZeje Z GddeZ Gd d eZ Gd d eZ dS) zSiglip model configurationN)Union)PretrainedConfig)loggingczeZdZdZdZ dfd Zedeee j fddfdZ xZ S)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} @gelu_pytorch_tanhư>c  tjd| | | d| ||_||_||_||_||_||_||_||_ | |_ 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_dropout)selfrrrrr r!r#r"r$rrrkwargs __class__s k/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/siglip/configuration_siglip.pyrzSiglipTextConfig.__init__Ssy$ sl\hsslrsss$&!2!2#6 '>$,$!2pretrained_model_name_or_pathreturnrc N|||j|fi|\}}|ddkr|d}d|vrMt|dr=|d|jkr,t d|dd|jd|j|fi|S)N model_typesiglip text_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors._set_token_in_kwargsget_config_dictgethasattrr-loggerwarning from_dictclsr*r& config_dicts r(from_pretrainedz SiglipTextConfig.from_pretrainedqs   (((1c12OZZSYZZ V ??< ( (H 4 4%m4K ; & &73 +E+E &+VbJcgjguJuJu NNr\1Jrr>rrr    s}[33F333r)) r r r r r rrrrrrr __name__ __module__ __qualname____doc__r-r classmethodrstrosPathLiker> __classcell__r's@r(rrs3 3 j%J "&333333<4E#r{BR