o Zh3@sxdZddlmZmZer ddlmZddlmZee Z GdddeZ Gdd d eZ Gd d d eZ gd Zd S)zOWLv2 model configuration) TYPE_CHECKINGDict)PretrainedConfig)loggingcsFeZdZdZdZdZ         dfdd ZZS)Owlv2TextConfigaw This is the configuration class to store the configuration of an [`Owlv2TextModel`]. It is used to instantiate an Owlv2 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 Owlv2 [google/owlv2-base-patch16](https://huggingface.co/google/owlv2-base-patch16) 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 OWLv2 text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Owlv2TextModel`]. 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 Owlv2TextConfig, Owlv2TextModel >>> # Initializing a Owlv2TextModel with google/owlv2-base-patch16 style configuration >>> configuration = Owlv2TextConfig() >>> # Initializing a Owlv2TextConfig from the google/owlv2-base-patch16 style configuration >>> model = Owlv2TextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zowlv2_text_model text_config  quick_geluh㈵>{Gz??rc s`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_embeddings hidden_actlayer_norm_epsattention_dropoutinitializer_rangeinitializer_factor)selfrrrrr r!r"r#r$r%r&rrrkwargs __class__r\/var/www/auris/lib/python3.10/site-packages/transformers/models/owlv2/configuration_owlv2.pyr^s zOwlv2TextConfig.__init__)r r r r r rrrrrrrrr__name__ __module__ __qualname____doc__ model_typeZbase_config_keyr __classcell__rrr)r+rs&;rcsBeZdZdZdZdZ        dfdd ZZS)Owlv2VisionConfigaY This is the configuration class to store the configuration of an [`Owlv2VisionModel`]. It is used to instantiate an OWLv2 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 OWLv2 [google/owlv2-base-patch16](https://huggingface.co/google/owlv2-base-patch16) 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 16): 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 Owlv2VisionConfig, Owlv2VisionModel >>> # Initializing a Owlv2VisionModel with google/owlv2-base-patch16 style configuration >>> configuration = Owlv2VisionConfig() >>> # Initializing a Owlv2VisionModel model from the google/owlv2-base-patch16 style configuration >>> model = Owlv2VisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zowlv2_vision_model vision_config r rrrrrrrc  s^tjdi| ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ dS)Nr)rrrrrr num_channels image_size patch_sizer"r#r$r%r&)r'rrrr r7r8r9r"r#r$r%r&r(r)rr+rs zOwlv2VisionConfig.__init__) r5r6r r rr5rrrrrrr,rrr)r+r3s"4r3csPeZdZdZdZeedZ     dfdd Ze d e d e fd d Z Z S) Owlv2Configa [`Owlv2Config`] is the configuration class to store the configuration of an [`Owlv2Model`]. It is used to instantiate an OWLv2 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 OWLv2 [google/owlv2-base-patch16](https://huggingface.co/google/owlv2-base-patch16) 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 [`Owlv2TextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Owlv2VisionConfig`]. 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 OWLv2 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. Zowlv2)rr4Nr /L F@Tc sztjdi||duri}td|duri}tdtdi||_tdi||_||_||_ ||_ d|_ dS)NzJtext_config is None. Initializing the Owlv2TextConfig with default values.zNvision_config is None. initializing the Owlv2VisionConfig with default values.rr) rrloggerinforrr3r4projection_dimlogit_scale_init_value return_dictr&)r'rr4r>r?r@r(r)rr+rs    zOwlv2Config.__init__rr4cKs&i}||d<||d<|j|fi|S)z Instantiate a [`Owlv2Config`] (or a derived class) from owlv2 text model configuration and owlv2 vision model configuration. Returns: [`Owlv2Config`]: An instance of a configuration object rr4) from_dict)clsrr4r(Z config_dictrrr+from_text_vision_configss z$Owlv2Config.from_text_vision_configs)NNr r;T) r-r.r/r0r1rr3Z sub_configsr classmethodrrCr2rrr)r+r:s r:)r:rr3N)r0typingrrZconfiguration_utilsrutilsrZ get_loggerr-r<rr3r:__all__rrrr+s   aY H