o h =@sdZddlZddlmZmZmZer ddlmZddlm Z e e Z ddiZ Gd d d eZGd d d eZGd ddeZdS)z OWLv2 model configurationN) TYPE_CHECKINGDictUnion)PretrainedConfig)loggingzgoogle/owlv2-base-patch16zIhttps://huggingface.co/google/owlv2-base-patch16/resolve/main/config.jsoncsbeZdZdZdZ         dfdd Zedeee j fddfddZ Z S)Owlv2TextConfigax 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 ```owlv2_text_model  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)selfrrrr r!r"r#r$r%r&r'rrrkwargs __class__rc/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/owlv2/configuration_owlv2.pyrbs zOwlv2TextConfig.__init__pretrained_model_name_or_pathreturnrcK|||j|fi|\}}|ddkr|d}d|vr:t|dr:|d|jkr:td|dd|jd|j|fi|S)N model_typeowlv2 text_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors._set_token_in_kwargsget_config_dictgethasattrr0loggerwarning from_dictclsr-r) config_dictrrr,from_pretrained   zOwlv2TextConfig.from_pretrained)r r r r rrrrrrrrrr __name__ __module__ __qualname____doc__r0r classmethodrstrosPathLikerA __classcell__rrr*r,r$s(; &rcs^eZdZdZdZ         dfd d Zedeee j fddfddZ Z S)Owlv2VisionConfigaZ 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 ```owlv2_vision_model r rrrrrrrc  s^tjdi| ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ dS)Nr)rrrrr r! num_channels image_size patch_sizer#r$r%r&r')r(rrr r!rQrRrSr#r$r%r&r'r)r*rr,rs zOwlv2VisionConfig.__init__r-r.rcKr/)Nr0r1 vision_configr3r4r5r6r>rrr,rArBz!Owlv2VisionConfig.from_pretrained) rOrPr r rrOrrrrrrrCrrr*r,rMs$4&rMcsfeZdZdZdZ     dfdd Zed eee j fd d fd d Z ede de fddZ ZS) 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 inital 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. r1Nr /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) rrr;inforr2rMrTprojection_dimlogit_scale_init_value return_dictr')r(r2rTrXrYrZr)r*rr,rs    zOwlv2Config.__init__r-r.rcKsp|||j|fi|\}}d|vr/t|dr/|d|jkr/td|dd|jd|j|fi|S)Nr0r3r4r5)r7r8r:r0r;r<r=r>rrr,rA7s   zOwlv2Config.from_pretrainedr2rTcKs&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 r2rT)r=)r?r2rTr)r@rrr,from_text_vision_configsEs z$Owlv2Config.from_text_vision_configs)NNr rVT)rDrErFrGr0rrHrrIrJrKrArr[rLrrr*r,rUs rU)rGrJtypingrrrconfiguration_utilsrutilsr get_loggerrDr;#OWLV2_PRETRAINED_CONFIG_ARCHIVE_MAPrrMrUrrrr,s   rj