
    <h>                         S r SSKJr  SSKJr  \R
                  " \5      r " S S\5      r " S S\5      r	 " S S	\5      r
/ S
Qrg)zALIGN model configuration   )PretrainedConfig)loggingc                   V   ^  \ rS rSrSrSrSr               SU 4S jjrSrU =r	$ )AlignTextConfig   a  
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://huggingface.co/papers/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://huggingface.co/papers/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U ]  " S0 UD6  Xl        X l        X0l        X@l        X`l        XPl        Xpl        Xl	        Xl
        Xl        Xl        Xl        Xl        Xl        Xl        g )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                    e/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/align/configuration_align.pyr   AlignTextConfig.__init__]   sl    & 	"6"$&!2#6 $!2#6 ,H)'>$.!2,'>$"(    )r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   )i:w  i      r#   i   gelu皙?r%   i      {Gz?g-q=    absoluteT)
__name__
__module____qualname____firstlineno____doc__
model_typebase_config_keyr   __static_attributes____classcell__r   s   @r    r   r      sN    ?B $J#O %( # *!#) #)r"   r   c            )          ^  \ rS rSrSrSrSrSSSSS	/ S
Q/ SQ/ SQ/ / SQ/ SQ/ SQSSSSSSSS4S\S\S\S\S\S\	\   S\	\   S\	\   S \	\   S!\	\   S"\	\   S#\	\   S$\S%\
S&\S'\
S(\S)\S*\S+\4(U 4S, jjjrS-rU =r$ ).AlignVisionConfig   a  
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   r:   r:   r   )       r   (   P   p      )r<   r   r=   r>   r?   r@   i@  )   r&   r&   r&   rA   r&   rA   )rA   r&   r&   r   r      rA   )rA      rC   rC   rC   rC   rC   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                 F  > [         TU ]  " S0 UD6  Xl        X l        X0l        X@l        XPl        X`l        Xpl        Xl	        Xl
        Xl        Xl        Xl        Xl        Xl        Xl        UU l        UU l        UU l        UU l        UU l        [-        U5      S-  U l        g )NrB   r   )r   r   rF   rG   rH   rI   rJ   rK   rL   rM   rN   rO   rP   rQ   rR   r   rS   rT   r   rU   rV   rW   sumr   )r   rF   rG   rH   rI   rJ   rK   rL   rM   rN   rO   rP   rQ   rR   r   rS   rT   r   rU   rV   rW   r   r   s                         r    r   AlignVisionConfig.__init__   s    0 	"6"($!2!2*(&(!2!2*'>$$$(!2,#6 !2!$%6!7!!;r"   )rU   rV   rI   rJ   rN   rW   rQ   r   rS   rG   rL   r   rK   rP   rF   r   rM   rT   rR   rO   rH   )r*   r+   r,   r-   r.   r/   r0   intfloatliststrr   r1   r2   r3   s   @r    r5   r5      s@   CJ &J%O #&#&"7!?"A')2'<#8)-!"#' %%)#&+.<.< .< !	.<
 !.< .< 3i.< #Y.< 3i.<  9.< c.<  9.< Cy.< "'.< .<  !.<" #.<$ !%.<& '.<( #).<* !+.< .<r"   r5   c                   H   ^  \ rS rSrSrSr\\S.r     SU 4S jjr	Sr
U =r$ )AlignConfig   ae  
[`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	   r8   c                    > [         TU ]  " S0 UD6  Uc  0 n[        R                  S5        Uc  0 n[        R                  S5        [	        S0 UD6U l        [        S0 UD6U l        X0l        X@l	        XPl
        g )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	   r5   r8   projection_dimtemperature_init_valuer   )r   r	   r8   rf   rg   r   r   r   s          r    r   AlignConfig.__init__0  sw     	"6"KKKde MKKhi*9[9.??,&<#!2r"   )r   rf   rg   r	   r8   )NNi  g      ?r'   )r*   r+   r,   r-   r.   r/   r   r5   sub_configsr   r1   r2   r3   s   @r    r`   r`      s6    -^ J"1DUVK "3 3r"   r`   )r   r5   r`   N)r.   configuration_utilsr   utilsr   
get_loggerr*   rd   r   r5   r`   __all__r   r"   r    <module>rn      sZ      3  
		H	%h)& h)Vw<( w<tK3" K3\ Br"   