
    sg@                         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g dZy)zALIGN model configuration    )TYPE_CHECKINGList   )PretrainedConfig)loggingc                   J     e Zd ZdZdZdZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )AlignTextConfigal  
    This is the configuration class to store the configuration of a [`AlignTextModel`]. It is used to instantiate a
    ALIGN 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 text encoder of the ALIGN
    [kakaobrain/align-base](https://huggingface.co/kakaobrain/align-base) architecture. The default values here are
    copied from BERT.

    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 30522):
            Vocabulary size of the Align Text model. Defines the number of different tokens that can be represented by
            the `inputs_ids` passed when calling [`AlignTextModel`].
        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 512):
            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` passed when calling [`AlignTextModel`].
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
            The epsilon used by the layer normalization layers.
        pad_token_id (`int`, *optional*, defaults to 0):
            Padding token id.
        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).
        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 AlignTextConfig, AlignTextModel

    >>> # Initializing a AlignTextConfig with kakaobrain/align-base style configuration
    >>> configuration = AlignTextConfig()

    >>> # Initializing a AlignTextModel (with random weights) from the kakaobrain/align-base style configuration
    >>> model = AlignTextModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```align_text_modeltext_configc                     t        |   di | || _        || _        || _        || _        || _        || _        || _        || _	        |	| _
        |
| _        || _        || _        || _        || _        || _        y )N )super__init__
vocab_sizehidden_sizenum_hidden_layersnum_attention_heads
hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_epsposition_embedding_type	use_cachepad_token_id)selfr   r   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/align/configuration_align.pyr   zAlignTextConfig.__init__c   s    & 	"6"$&!2#6 $!2#6 ,H)'>$.!2,'>$"(    )i:w  i      r$   i   gelu皙?r&   i      {Gz?g-q=r   absoluteT)__name__
__module____qualname____doc__
model_typebase_config_keyr   __classcell__r!   s   @r"   r	   r	      sN    ?B $J#O %( # *!#) #)r#   r	   c            )            e Zd ZdZdZdZdddddg d	g d
g dg g dg dg dddddddddfdedededededee   dee   dee   dee   d ee   d!ee   d"ee   d#ed$e	d%ed&e	d'ed(ed)ed*ef( fd+Z
 xZS ),AlignVisionConfiga  
    This is the configuration class to store the configuration of a [`AlignVisionModel`]. It is used to instantiate a
    ALIGN vision 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 vision encoder of the ALIGN
    [kakaobrain/align-base](https://huggingface.co/kakaobrain/align-base) architecture. The default values are copied
    from EfficientNet (efficientnet-b7)

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

    Args:
        num_channels (`int`, *optional*, defaults to 3):
            The number of input channels.
        image_size (`int`, *optional*, defaults to 600):
            The input image size.
        width_coefficient (`float`, *optional*, defaults to 2.0):
            Scaling coefficient for network width at each stage.
        depth_coefficient (`float`, *optional*, defaults to 3.1):
            Scaling coefficient for network depth at each stage.
        depth_divisor `int`, *optional*, defaults to 8):
            A unit of network width.
        kernel_sizes (`List[int]`, *optional*, defaults to `[3, 3, 5, 3, 5, 5, 3]`):
            List of kernel sizes to be used in each block.
        in_channels (`List[int]`, *optional*, defaults to `[32, 16, 24, 40, 80, 112, 192]`):
            List of input channel sizes to be used in each block for convolutional layers.
        out_channels (`List[int]`, *optional*, defaults to `[16, 24, 40, 80, 112, 192, 320]`):
            List of output channel sizes to be used in each block for convolutional layers.
        depthwise_padding (`List[int]`, *optional*, defaults to `[]`):
            List of block indices with square padding.
        strides (`List[int]`, *optional*, defaults to `[1, 2, 2, 2, 1, 2, 1]`):
            List of stride sizes to be used in each block for convolutional layers.
        num_block_repeats (`List[int]`, *optional*, defaults to `[1, 2, 2, 3, 3, 4, 1]`):
            List of the number of times each block is to repeated.
        expand_ratios (`List[int]`, *optional*, defaults to `[1, 6, 6, 6, 6, 6, 6]`):
            List of scaling coefficient of each block.
        squeeze_expansion_ratio (`float`, *optional*, defaults to 0.25):
            Squeeze expansion ratio.
        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
            The non-linear activation function (function or string) in each block. If string, `"gelu"`, `"relu"`,
            `"selu", `"gelu_new"`, `"silu"` and `"mish"` are supported.
        hidden_dim (`int`, *optional*, defaults to 1280):
            The hidden dimension of the layer before the classification head.
        pooling_type (`str` or `function`, *optional*, defaults to `"mean"`):
            Type of final pooling to be applied before the dense classification head. Available options are [`"mean"`,
            `"max"`]
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        batch_norm_eps (`float`, *optional*, defaults to 1e-3):
            The epsilon used by the batch normalization layers.
        batch_norm_momentum (`float`, *optional*, defaults to 0.99):
            The momentum used by the batch normalization layers.
        drop_connect_rate (`float`, *optional*, defaults to 0.2):
            The drop rate for skip connections.

    Example:

    ```python
    >>> from transformers import AlignVisionConfig, AlignVisionModel

    >>> # Initializing a AlignVisionConfig with kakaobrain/align-base style configuration
    >>> configuration = AlignVisionConfig()

    >>> # Initializing a AlignVisionModel (with random weights) from the kakaobrain/align-base style configuration
    >>> model = AlignVisionModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```align_vision_modelvision_configr   iX  g       @g@   )r   r      r   r7   r7   r   )          (   P   p      )r9   r:   r;   r<   r=   r>   i@  )   r'   r'   r'   r?   r'   r?   )r?   r'   r'   r   r      r?   )r?      rA   rA   rA   rA   rA   g      ?swishi 
  meanr(   gMbP?gGz?g?num_channels
image_sizewidth_coefficientdepth_coefficientdepth_divisorkernel_sizesin_channelsout_channelsdepthwise_paddingstridesnum_block_repeatsexpand_ratiossqueeze_expansion_ratior   
hidden_dimpooling_typer   batch_norm_epsbatch_norm_momentumdrop_connect_ratec                 b   t        |   di | || _        || _        || _        || _        || _        || _        || _        || _	        |	| _
        |
| _        || _        || _        || _        || _        || _        || _        || _        || _        || _        || _        t-        |      dz  | _        y )Nr@   r   )r   r   rD   rE   rF   rG   rH   rI   rJ   rK   rL   rM   rN   rO   rP   r   rQ   rR   r   rS   rT   rU   sumr   )r   rD   rE   rF   rG   rH   rI   rJ   rK   rL   rM   rN   rO   rP   r   rQ   rR   r   rS   rT   rU   r    r!   s                         r"   r   zAlignVisionConfig.__init__   s    0 	"6"($!2!2*(&(!2!2*'>$$$(!2,#6 !2!$%6!7!!;r#   )r*   r+   r,   r-   r.   r/   intfloatr   strr   r0   r1   s   @r"   r3   r3      s@   CJ &J%O #&#&"7!?"A')2'<#8)-!"#' %%)#&+.<.< .< !	.<
 !.< .< 3i.< #Y.< 3i.<  9.< c.<  9.< Cy.< "'.< .<  !.<" #.<$ !%.<& '.<( #).<* !+.< .<r#   r3   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 )	AlignConfiga  
    [`AlignConfig`] is the configuration class to store the configuration of a [`AlignModel`]. It is used to
    instantiate a ALIGN 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 ALIGN
    [kakaobrain/align-base](https://huggingface.co/kakaobrain/align-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:
        text_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`AlignTextConfig`].
        vision_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`AlignVisionConfig`].
        projection_dim (`int`, *optional*, defaults to 640):
            Dimensionality of text and vision projection layers.
        temperature_init_value (`float`, *optional*, defaults to 1.0):
            The initial value of the *temperature* parameter. Default is used as per the original ALIGN implementation.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        kwargs (*optional*):
            Dictionary of keyword arguments.

    Example:

    ```python
    >>> from transformers import AlignConfig, AlignModel

    >>> # Initializing a AlignConfig with kakaobrain/align-base style configuration
    >>> configuration = AlignConfig()

    >>> # Initializing a AlignModel (with random weights) from the kakaobrain/align-base style configuration
    >>> model = AlignModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config

    >>> # We can also initialize a AlignConfig from a AlignTextConfig and a AlignVisionConfig
    >>> from transformers import AlignTextConfig, AlignVisionConfig

    >>> # Initializing ALIGN Text and Vision configurations
    >>> config_text = AlignTextConfig()
    >>> config_vision = AlignVisionConfig()

    >>> config = AlignConfig.from_text_vision_configs(config_text, config_vision)
    ```alignr   r5   c                     t        |   di | |i }t        j                  d       |i }t        j                  d       t	        di || _        t        di || _        || _        || _	        || _
        y )NzJtext_config is None. Initializing the AlignTextConfig with default values.zNvision_config is None. Initializing the AlignVisionConfig with default values.r   )r   r   loggerinfor	   r   r3   r5   projection_dimtemperature_init_valuer   )r   r   r5   rb   rc   r   r    r!   s          r"   r   zAlignConfig.__init__6  s}     	"6"KKKde MKKhi*9[9.??,&<#!2r#   r   r5   c                 P     | d|j                         |j                         d|S )z
        Instantiate a [`AlignConfig`] (or a derived class) from align text model configuration and align vision model
        configuration.

        Returns:
            [`AlignConfig`]: An instance of a configuration object
        r^   r   )to_dict)clsr   r5   r    s       r"   from_text_vision_configsz$AlignConfig.from_text_vision_configsP  s,     f{224MDYDYD[f_effr#   )NNi  g      ?r(   )r*   r+   r,   r-   r.   r	   r3   sub_configsr   classmethodrg   r0   r1   s   @r"   r\   r\     sX    -^ J"1DUVK "34 	g? 	gSd 	g 	gr#   r\   )r	   r3   r\   N)r-   typingr   r   configuration_utilsr   utilsr   
get_loggerr*   r`   r	   r3   r\   __all__r   r#   r"   <module>ro      si      &  3  
		H	%h)& h)Vw<( w<tWg" Wgt Br#   