o Û·iN3ã@sbdZddlmZddlmZe e¡ZGdd„deƒZGdd„deƒZ Gdd „d eƒZ gd ¢Z d S) zOWLv2 model configurationé)ÚPretrainedConfig)ÚloggingcsFeZdZdZdZdZ         d‡fdd„ Z‡ZS)ÚOwlv2TextConfigaw 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 ```Úowlv2_text_modelÚ text_configéÁééé ééÚ quick_geluçñh㈵øä>çç{®Gáz”?çð?ééþÀéÿÀc s`tƒjd| | |dœ|¤Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ dS)N)Ú pad_token_idÚ bos_token_idÚ eos_token_id©) ÚsuperÚ__init__Ú vocab_sizeÚ hidden_sizeÚintermediate_sizeÚnum_hidden_layersÚnum_attention_headsÚmax_position_embeddingsÚ hidden_actÚlayer_norm_epsÚattention_dropoutÚinitializer_rangeÚinitializer_factor)Úselfrrrrrr r!r"r#r$r%rrrÚkwargs©Ú __class__rúc/home/ubuntu/vllm_env/lib/python3.10/site-packages/transformers/models/owlv2/configuration_owlv2.pyrXs zOwlv2TextConfig.__init__)rrr r r r r rrrrrrr©Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚbase_config_keyrÚ __classcell__rrr(r*rs&;ñrcsBeZdZdZdZdZ        d‡fdd„ Z‡ZS)ÚOwlv2VisionConfigaY 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 ```Úowlv2_vision_modelÚ vision_configéé r rr r rrrrc  s^tƒjdi| ¤Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ dS)Nr)rrrrrrÚ num_channelsÚ image_sizeÚ patch_sizer!r"r#r$r%)r&rrrrr8r9r:r!r"r#r$r%r'r(rr*r²s zOwlv2VisionConfig.__init__) r6r7r r rr6r r rrrrr+rrr(r*r3zs"4ór3csPeZdZdZdZeedœZ     d‡fdd „ Ze d e d e fd d „ƒZ ‡Z S)Ú 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. Úowlv2)rr5Nrçƒ/L¦ F@Tc sztƒjdi|¤Ž|duri}t d¡|duri}t d¡tdi|¤Ž|_tdi|¤Ž|_||_||_ ||_ d|_ dS)NzJtext_config is None. Initializing the Owlv2TextConfig with default values.zNvision_config is None. initializing the Owlv2VisionConfig with default values.rr) rrÚloggerÚinforrr3r5Úprojection_dimÚlogit_scale_init_valueÚ return_dictr%)r&rr5r@rArBr'r(rr*rðs    zOwlv2Config.__init__rr5cKs&i}||d<||d<|j|fi|¤ŽS)zë 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 rr5)Ú from_dict)Úclsrr5r'Ú config_dictrrr*Úfrom_text_vision_configs s z$Owlv2Config.from_text_vision_configs)NNrr=T) r,r-r.r/r0rr3Ú sub_configsrÚ classmethodÚdictrFr2rrr(r*r;Ós úr;)r;rr3N) r/Úconfiguration_utilsrÚutilsrÚ get_loggerr,r>rr3r;Ú__all__rrrr*Ús   aY H