
    sgO3                         d Z ddlmZmZ er	 ddlmZ ddlmZ  ej                  e	      Z
 G d de      Z G d d	e      Z G d
 de      Zy)zOWLv2 model configuration    )TYPE_CHECKINGDict   )PretrainedConfig)loggingc                   H     e Zd ZdZdZdZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )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
    ```owlv2_text_modeltext_configc                     t        |   d|||d| || _        || _        || _        || _        || _        || _        || _        || _	        |	| _
        |
| _        || _        y )N)pad_token_idbos_token_ideos_token_id )super__init__
vocab_sizehidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsmax_position_embeddings
hidden_actlayer_norm_epsattention_dropoutinitializer_rangeinitializer_factor)selfr   r   r   r   r   r   r   r   r   r   r   r   r   r   kwargs	__class__s                   `/var/www/html/venv/lib/python3.12/site-packages/transformers/models/owlv2/configuration_owlv2.pyr   zOwlv2TextConfig.__init__^   sv    $ 	sl\hslrs$&!2!2#6 '>$$,!2!2"4    )i      i            
quick_geluh㈵>        {Gz?      ?r   i  i  __name__
__module____qualname____doc__
model_typebase_config_keyr   __classcell__r    s   @r!   r	   r	      sK    9v $J#O  "5 5r"   r	   c                   D     e Zd ZdZdZdZ	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )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
    ```owlv2_vision_modelvision_configc                     t        |   di | || _        || _        || _        || _        || _        || _        || _        || _	        |	| _
        |
| _        || _        || _        y )Nr   )r   r   r   r   r   r   num_channels
image_size
patch_sizer   r   r   r   r   )r   r   r   r   r   r:   r;   r<   r   r   r   r   r   r   r    s                 r!   r   zOwlv2VisionConfig.__init__   sr      	"6"&!2!2#6 ($$$,!2!2"4r"   )   i   r$   r$   r   r=   r&   r'   r(   r)   r*   r+   r,   r4   s   @r!   r6   r6      sE    2h &J%O 5 5r"   r6   c                   V     e Zd ZdZdZeedZ	 	 	 	 	 d fd	Ze	de
de
fd       Z x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.
    owlv2)r   r8   c                     t        |   di | |i }t        j                  d       |i }t        j                  d       t	        di || _        t        di || _        || _        || _	        || _
        d| _        y )NzJtext_config is None. Initializing the Owlv2TextConfig with default values.zNvision_config is None. initializing the Owlv2VisionConfig with default values.r+   r   )r   r   loggerinfor	   r   r6   r8   projection_dimlogit_scale_init_valuereturn_dictr   )r   r   r8   rD   rE   rF   r   r    s          r!   r   zOwlv2Config.__init__   s     	"6"KKKde MKKhi*9[9.??,&<#&"%r"   r   r8   c                 @    i }||d<   ||d<    | j                   |fi |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
        r   r8   )	from_dict)clsr   r8   r   config_dicts        r!   from_text_vision_configsz$Owlv2Config.from_text_vision_configs  s3     %0M"'4O$s}}[3F33r"   )NNr#   g/L
F@T)r-   r.   r/   r0   r1   r	   r6   sub_configsr   classmethodr   rK   r3   r4   s   @r!   r?   r?      sR    2 J"1DUVK %&6 44 4 4 4r"   r?   N)r0   typingr   r   configuration_utilsr   utilsr   
get_loggerr-   rB   r	   r6   r?   r   r"   r!   <module>rR      s^      &  3  
		H	%]5& ]5BU5( U5rE4" E4r"   