
    sg9                         d Z 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BridgeTower model configuration   )PretrainedConfig)loggingc                   @     e Zd ZdZdZdZ	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )BridgeTowerVisionConfiga  
    This is the configuration class to store the vision configuration of a [`BridgeTowerModel`]. Instantiating a
    configuration with the defaults will yield a similar configuration to that of the bridgetower-base
    [BridgeTower/bridgetower-base](https://huggingface.co/BridgeTower/bridgetower-base/) 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.
        num_hidden_layers (`int`, *optional*, defaults to 12):
            Number of hidden layers in visual encoder model.
        patch_size (`int`, *optional*, defaults to 16):
            The size (resolution) of each patch.
        image_size (`int`, *optional*, defaults to 288):
            The size (resolution) of each image.
        initializer_factor (`float`, *optional*, defaults to 1):
            A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
            testing).
        layer_norm_eps (`float`, *optional*, defaults to 1e-05):
            The epsilon used by the layer normalization layers.
        stop_gradient (`bool`, *optional*, defaults to `False`):
            Whether to stop gradient for training.
        share_layernorm (`bool`, *optional*, defaults to `True`):
            Whether LayerNorm layers are shared.
        remove_last_layer (`bool`, *optional*, defaults to `False`):
            Whether to remove the last layer from the vision encoder.


    Example:

    ```python
    >>> from transformers import BridgeTowerVisionConfig

    >>> # Initializing a BridgeTower BridgeTower/bridgetower-base style configuration for the vision model
    >>> configuration = BridgeTowerVisionConfig()

    >>> # Accessing the configuration
    >>> configuration
    ```bridgetower_vision_modelvision_configc                     t        |   di | || _        || _        || _        || _        || _        || _        || _        || _	        |	| _
        |
| _        y N )super__init__hidden_sizenum_hidden_layersnum_channels
patch_size
image_sizeinitializer_factorlayer_norm_epsstop_gradientshare_layernormremove_last_layer)selfr   r   r   r   r   r   r   r   r   r   kwargs	__class__s               l/var/www/html/venv/lib/python3.12/site-packages/transformers/models/bridgetower/configuration_bridgetower.pyr   z BridgeTowerVisionConfig.__init__F   sc     	"6"&!2($$"4,*.!2    )
      r      i      h㈵>FTF__name__
__module____qualname____doc__
model_typebase_config_keyr   __classcell__r   s   @r   r   r      s?    (T ,J%O 3 3r   r   c                   N     e Zd ZdZdZdZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )BridgeTowerTextConfiga  
    This is the configuration class to store the text configuration of a [`BridgeTowerModel`]. The default values here
    are copied from RoBERTa. Instantiating a configuration with the defaults will yield a similar configuration to that
    of the bridgetower-base [BridegTower/bridgetower-base](https://huggingface.co/BridgeTower/bridgetower-base/)
    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 50265):
            Vocabulary size of the text part of the model. Defines the number of different tokens that can be
            represented by the `inputs_ids` passed when calling [`BridgeTowerModel`].
        hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        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.
        intermediate_size (`int`, *optional*, defaults to 3072):
            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
        hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"silu"` and `"gelu_new"` are supported.
        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        max_position_embeddings (`int`, *optional*, defaults to 514):
            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).
        type_vocab_size (`int`, *optional*, defaults to 2):
            The vocabulary size of the `token_type_ids`.
        initializer_factor (`float`, *optional*, defaults to 1):
            A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
            testing).
        layer_norm_eps (`float`, *optional*, defaults to 1e-05):
            The epsilon used by the layer normalization layers.
        position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
            Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
            positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
            [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
            For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
            with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
        is_decoder (`bool`, *optional*, defaults to `False`):
            Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models). Only
            relevant if `config.is_decoder=True`.

    Example:

    ```python
    >>> from transformers import BridgeTowerTextConfig

    >>> # Initializing a BridgeTower BridgeTower/bridgetower-base style configuration for the text model
    >>> configuration = BridgeTowerTextConfig()

    >>> # Accessing the configuration
    >>> configuration
    ```bridgetower_text_modeltext_configc                    t        |   di | || _        || _        || _        || _        || _        || _        || _        || _	        |	| _
        |
| _        || _        || _        || _        || _        || _        || _        || _        y r
   )r   r   
vocab_sizer   r   num_attention_heads
hidden_actr   intermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizer   position_embedding_type	use_cachepad_token_idbos_token_ideos_token_id)r   r0   r   r   r1   r   r3   r2   r4   r5   r6   r7   r   r:   r;   r<   r8   r9   r   r   s                      r   r   zBridgeTowerTextConfig.__init__   s    * 	"6"$&!2#6 $"4!2#6 ,H)'>$.,'>$"(((r   )iY  r   r   r   r    i   gelu皙?r>   i  r    r!   r           absoluteTr"   r*   s   @r   r,   r,   a   sT    <| *J#O %( # *%') ')r   r,   c                   f     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 )	BridgeTowerConfiga~  
    This is the configuration class to store the configuration of a [`BridgeTowerModel`]. It is used to instantiate a
    BridgeTower model according to the specified arguments, defining the model architecture. Instantiating a
    configuration with the defaults will yield a similar configuration to that of the bridgetower-base
    [BridgeTower/bridgetower-base](https://huggingface.co/BridgeTower/bridgetower-base/) architecture.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.

    Args:
        share_cross_modal_transformer_layers (`bool`, *optional*, defaults to `True`):
            Whether cross modal transformer layers are shared.
        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler.
        hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        initializer_factor (`float`, *optional*, defaults to 1):
            A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
            testing).
        layer_norm_eps (`float`, *optional*, defaults to 1e-05):
            The epsilon used by the layer normalization layers.
        share_link_tower_layers (`bool`, *optional*, defaults to `False`):
            Whether the bride/link tower layers are shared.
        link_tower_type (`str`, *optional*, defaults to `"add"`):
            Type of the bridge/link layer.
        num_attention_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        num_hidden_layers (`int`, *optional*, defaults to 6):
            Number of hidden layers in the Transformer encoder.
        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
            Whether to tie input and output embeddings.
        init_layernorm_from_vision_encoder (`bool`, *optional*, defaults to `False`):
            Whether to init LayerNorm from the vision encoder.
        text_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`BridgeTowerTextConfig`].
        vision_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`BridgeTowerVisionConfig`].

    Example:

    ```python
    >>> from transformers import BridgeTowerModel, BridgeTowerConfig

    >>> # Initializing a BridgeTower BridgeTower/bridgetower-base style configuration
    >>> configuration = BridgeTowerConfig()

    >>> # Initializing a model from the BridgeTower/bridgetower-base style configuration
    >>> model = BridgeTowerModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```bridgetowerr.   r   c                    |j                  dd       }|j                  dd       }t        |   di | || _        || _        || _        || _        || _        || _        || _	        || _
        |	| _        |
| _        || _        |i }t        j                  d       |i }t        j                  d       t!        di || _        t%        di || _        y )Ntext_config_dictvision_config_dictzV`text_config` is `None`. Initializing the `BridgeTowerTextConfig` with default values.zZ`vision_config` is `None`. Initializing the `BridgeTowerVisionConfig` with default values.r   )popr   r   $share_cross_modal_transformer_layersr2   r   r   r   share_link_tower_layerslink_tower_typer1   r   tie_word_embeddings"init_layernorm_from_vision_encoderloggerinfor,   r.   r   r   )r   rJ   r2   r   r   r   rK   rL   r1   r   rM   rN   r.   r   r   _r   s                   r   r   zBridgeTowerConfig.__init__  s    $ JJ)40JJ+T2"6"4X1$&"4,'>$.#6 !2#6 2T/KKKpq MKKtu0?;?4E}Er   r.   r   c                 P     | d|j                         |j                         d|S )z
        Instantiate a [`BridgeTowerConfig`] (or a derived class) from BridgeTower text model configuration. Returns:
            [`BridgeTowerConfig`]: An instance of a configuration object
        rE   r   )to_dict)clsr.   r   r   s       r   from_text_vision_configsz*BridgeTowerConfig.from_text_vision_configs3  s,     f{224MDYDYD[f_effr   )Tr=   r   r    r!   Faddr      FFNN)r#   r$   r%   r&   r'   r,   r   sub_configsr   classmethodrU   r)   r*   s   @r   rC   rC      ss    3j J"7JabK .2 %!+0+FZ g/g@Wg gr   rC   N)r&   configuration_utilsr   utilsr   
get_loggerr#   rO   r   r,   rC   r   r   r   <module>r]      sU    & 3  
		H	%F3. F3Ri), i)Xog( ogr   