Ë
    T^(h\  ã                   ó`   — d Z ddlmZ ddlmZ  ej
                  e«      Z G d„ de«      ZdgZ	y)zSegGpt model configurationé   )ÚPretrainedConfig)Úloggingc                   óV   ‡ — e Zd ZdZdZddddddd	d
dgdddddddddg d¢dfˆ fd„	Zˆ xZS )ÚSegGptConfigaœ  
    This is the configuration class to store the configuration of a [`SegGptModel`]. It is used to instantiate a SegGPT
    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 SegGPT
    [BAAI/seggpt-vit-large](https://huggingface.co/BAAI/seggpt-vit-large) 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 1024):
            Dimensionality of the encoder layers and the pooler layer.
        num_hidden_layers (`int`, *optional*, defaults to 24):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer encoder.
        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"selu"` and `"gelu_new"` are supported.
        hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        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-06):
            The epsilon used by the layer normalization layers.
        image_size (`List[int]`, *optional*, defaults to `[896, 448]`):
            The size (resolution) of each image.
        patch_size (`int`, *optional*, defaults to 16):
            The size (resolution) of each patch.
        num_channels (`int`, *optional*, defaults to 3):
            The number of input channels.
        qkv_bias (`bool`, *optional*, defaults to `True`):
            Whether to add a bias to the queries, keys and values.
        mlp_dim (`int`, *optional*):
            The dimensionality of the MLP layer in the Transformer encoder. If unset, defaults to
            `hidden_size` * 4.
        drop_path_rate (`float`, *optional*, defaults to 0.1):
            The drop path rate for the dropout layers.
        pretrain_image_size (`int`, *optional*, defaults to 224):
            The pretrained size of the absolute position embeddings.
        decoder_hidden_size (`int`, *optional*, defaults to 64):
            Hidden size for decoder.
        use_relative_position_embeddings (`bool`, *optional*, defaults to `True`):
            Whether to use relative position embeddings in the attention layers.
        merge_index (`int`, *optional*, defaults to 2):
            The index of the encoder layer to merge the embeddings.
        intermediate_hidden_state_indices (`List[int]`, *optional*, defaults to `[5, 11, 17, 23]`):
            The indices of the encoder layers which we store as features for the decoder.
        beta (`float`, *optional*, defaults to 0.01):
            Regularization factor for SegGptLoss (smooth-l1 loss).

    Example:

    ```python
    >>> from transformers import SegGptConfig, SegGptModel

    >>> # Initializing a SegGPT seggpt-vit-large style configuration
    >>> configuration = SegGptConfig()

    >>> # Initializing a model (with random weights) from the seggpt-vit-large style configuration
    >>> model = SegGptModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```Úseggpti   é   é   Úgelug        g{®Gáz”?g�íµ ÷Æ°>i€  iÀ  r   TNgš™™™™™¹?éà   é@   é   )é   é   é   é   g{®Gáz„?c                 ó˜  •— t        ‰| �  di |¤Ž |t        |«      kD  rt        d|›d|›�«      ‚|| _        || _        || _        || _        || _        || _	        || _
        || _        |	| _        |
| _        || _        || _        || _        || _        || _        || _        || _        || _        |€t-        |dz  «      | _        y || _        y )NzTMerge index must be less than the minimum encoder output index, but got merge_index=z' and intermediate_hidden_state_indices=é   © )ÚsuperÚ__init__ÚminÚ
ValueErrorÚhidden_sizeÚnum_hidden_layersÚnum_attention_headsÚ
hidden_actÚhidden_dropout_probÚinitializer_rangeÚlayer_norm_epsÚ
image_sizeÚ
patch_sizeÚnum_channelsÚqkv_biasÚdrop_path_rateÚpretrain_image_sizeÚdecoder_hidden_sizeÚ use_relative_position_embeddingsÚmerge_indexÚ!intermediate_hidden_state_indicesÚbetaÚintÚmlp_dim)Úselfr   r   r   r   r   r   r   r    r!   r"   r#   r,   r$   r%   r&   r'   r(   r)   r*   ÚkwargsÚ	__class__s                        €úm/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/seggpt/configuration_seggpt.pyr   zSegGptConfig.__init__]   sû   ø€ ô. 	‰ÑÑ"˜6Ò"àœÐ>Ó?Ò?ÜØgÐ[fÐZhð  iQð  oPð  nRð  Sóð ð 'ˆÔØ!2ˆÔØ#6ˆÔ Ø$ˆŒØ#6ˆÔ Ø!2ˆÔØ,ˆÔØ$ˆŒØ$ˆŒØ(ˆÔØ ˆŒØ,ˆÔØ#6ˆÔ Ø#6ˆÔ Ø0PˆÔ-Ø&ˆÔØ1RˆÔ.ØˆŒ	Ø/6¨”s˜;¨™?Ó+ˆ�ÀGˆ�ó    )Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typer   Ú__classcell__)r/   s   @r0   r   r      s\   ø„ ñ@ðD €Jð ØØØØØØØ˜�:ØØØØØØØØ)-ØÚ*9Ø÷)/Lñ /Lr1   r   N)
r5   Úconfiguration_utilsr   Úutilsr   Ú
get_loggerr2   Úloggerr   Ú__all__r   r1   r0   ú<module>r=      s@   ðñ !å 3Ý ð 
ˆ×	Ñ	˜HÓ	%€ôtLÐ#ô tLðn Ð
�r1   