qi^0dZddlmZddlmZej eZGddeZGddeZ Gdd eZ gd Z y ) zOWL-ViT model configuration)PreTrainedConfig)loggingcHeZdZdZdZdZ dfd ZxZS)OwlViTTextConfiga This is the configuration class to store the configuration of an [`OwlViTTextModel`]. It is used to instantiate an OwlViT 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 OwlViT [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32) 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 49408): Vocabulary size of the OWL-ViT text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`OwlViTTextModel`]. hidden_size (`int`, *optional*, defaults to 512): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 2048): 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 8): Number of attention heads for each attention layer in the Transformer encoder. max_position_embeddings (`int`, *optional*, defaults to 16): 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 `"quick_gelu"`): 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-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). pad_token_id (`int`, *optional*, defaults to 0): The id of the padding token in the input sequences. bos_token_id (`int`, *optional*, defaults to 49406): The id of the beginning-of-sequence token in the input sequences. eos_token_id (`int`, *optional*, defaults to 49407): The id of the end-of-sequence token in the input sequences. Example: ```python >>> from transformers import OwlViTTextConfig, OwlViTTextModel >>> # Initializing a OwlViTTextModel with google/owlvit-base-patch32 style configuration >>> configuration = OwlViTTextConfig() >>> # Initializing a OwlViTTextConfig from the google/owlvit-base-patch32 style configuration >>> model = OwlViTTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```owlvit_text_model text_configc t|di|| |_| |_||_||_||_||_||_||_ ||_ ||_ ||_ | |_ | |_| |_yN)super__init__ pad_token_id bos_token_id eos_token_id vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsmax_position_embeddings hidden_actlayer_norm_epsattention_dropoutinitializer_rangeinitializer_factor)selfrrrrrrrrrrrrrrkwargs __class__s a/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/owlvit/configuration_owlvit.pyr zOwlViTTextConfig.__init__Vs$ "6"((($&!2!2#6 '>$$,!2!2"4)ii  quick_geluh㈵>{Gz??ii__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__rs@rrrsK9 v%J#O "!5!5r rcDeZdZdZdZdZ dfd ZxZS)OwlViTVisionConfigah This is the configuration class to store the configuration of an [`OwlViTVisionModel`]. It is used to instantiate an OWL-ViT image 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 OWL-ViT [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32) 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 768): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 32): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): 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-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). Example: ```python >>> from transformers import OwlViTVisionConfig, OwlViTVisionModel >>> # Initializing a OwlViTVisionModel with google/owlvit-base-patch32 style configuration >>> configuration = OwlViTVisionConfig() >>> # Initializing a OwlViTVisionModel model from the google/owlvit-base-patch32 style configuration >>> model = OwlViTVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```owlvit_vision_model vision_configc  t|di| ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ yr )r r rrrr num_channels image_size patch_sizerrrrr)rrrrrr9r:r;rrrrrrrs rr zOwlViTVisionConfig.__init__sr "6"&!2!2#6 ($$$,!2!2"4r ) i r"r"rr< r%r&r'r(r)r+r3s@rr5r5zsE2 h'J%O55r r5c<eZdZdZdZeedZ dfd ZxZ S) OwlViTConfiga [`OwlViTConfig`] is the configuration class to store the configuration of an [`OwlViTModel`]. It is used to instantiate an OWL-ViT 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 OWL-ViT [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32) 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 [`OwlViTTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`OwlViTVisionConfig`]. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and vision projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The initial value of the *logit_scale* parameter. Default is used as per the original OWL-ViT implementation. return_dict (`bool`, *optional*, defaults to `True`): Whether or not the model should return a dictionary. If `False`, returns a tuple. kwargs (*optional*): Dictionary of keyword arguments. owlvit)rr7c l| t}tjdnt|tr tdi|}| t }tjdnt|tr t di|}||_||_||_||_ ||_ d|_ t|4di|y)NzQ`text_config` is `None`. initializing the `OwlViTTextConfig` with default values.zU`vision_config` is `None`. initializing the `OwlViTVisionConfig` with default values.r)r )rloggerinfo isinstancedictr5rr7projection_dimlogit_scale_init_value return_dictrr r )rrr7rFrGrHrrs rr zOwlViTConfig.__init__s  *,K KKk l  T **9[9K  .0M KKo p  t ,.??M&*,&<#&"% "6"r )NNr!g/L F@T) r,r-r.r/r0rr5 sub_configsr r2r3s@rr?r?s52J"2EWXK% ##r r?)r?rr5N) r/configuration_utilsrutilsr get_loggerr,rBrr5r?__all__r r rrNsZ"3   H %`5'`5FU5)U5p9##9#x Er