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TrOCR model configurationé   )ÚPretrainedConfig)Úloggingc                   ób   ‡ — e Zd ZdZdZdgZddddœZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 d	ˆ fd„	Zˆ xZS )
ÚTrOCRConfigaÆ  
    This is the configuration class to store the configuration of a [`TrOCRForCausalLM`]. It is used to instantiate an
    TrOCR 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 TrOCR
    [microsoft/trocr-base-handwritten](https://huggingface.co/microsoft/trocr-base-handwritten) 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 TrOCR model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`TrOCRForCausalLM`].
        d_model (`int`, *optional*, defaults to 1024):
            Dimensionality of the layers and the pooler layer.
        decoder_layers (`int`, *optional*, defaults to 12):
            Number of decoder layers.
        decoder_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer decoder.
        decoder_ffn_dim (`int`, *optional*, defaults to 4096):
            Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.
        activation_function (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the pooler. If string, `"gelu"`, `"relu"`,
            `"silu"` and `"gelu_new"` are supported.
        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).
        dropout (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, and pooler.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        activation_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for activations inside the fully connected layer.
        init_std (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        decoder_layerdrop (`float`, *optional*, defaults to 0.0):
            The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
            for more details.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        scale_embedding (`bool`, *optional*, defaults to `False`):
            Whether or not to scale the word embeddings by sqrt(d_model).
        use_learned_position_embeddings (`bool`, *optional*, defaults to `True`):
            Whether or not to use learned position embeddings. If not, sinusoidal position embeddings will be used.
        layernorm_embedding (`bool`, *optional*, defaults to `True`):
            Whether or not to use a layernorm after the word + position embeddings.

    Example:

    ```python
    >>> from transformers import TrOCRConfig, TrOCRForCausalLM

    >>> # Initializing a TrOCR-base style configuration
    >>> configuration = TrOCRConfig()

    >>> # Initializing a model (with random weights) from the TrOCR-base style configuration
    >>> model = TrOCRForCausalLM(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```ÚtrocrÚpast_key_valuesÚdecoder_attention_headsÚd_modelÚdecoder_layers)Únum_attention_headsÚhidden_sizeÚnum_hidden_layersc                 ó  •— || _         || _        || _        || _        || _        || _        || _        || _        |	| _        |
| _	        || _
        || _        || _        || _        || _        || _        t!        ‰| �D  d||||dœ|¤Ž y )N)Úpad_token_idÚbos_token_idÚeos_token_idÚdecoder_start_token_id© )Ú
vocab_sizer
   r   r	   Údecoder_ffn_dimÚactivation_functionÚmax_position_embeddingsÚdropoutÚattention_dropoutÚactivation_dropoutÚinit_stdÚdecoder_layerdropÚ	use_cacheÚscale_embeddingÚuse_learned_position_embeddingsÚlayernorm_embeddingÚsuperÚ__init__)Úselfr   r
   r   r	   r   r   r   r   r   r   r   r   r   r   r   r    r!   r   r   r   ÚkwargsÚ	__class__s                         €úk/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/trocr/configuration_trocr.pyr#   zTrOCRConfig.__init__`   s¨   ø€ ð0 %ˆŒØˆŒØ,ˆÔØ'>ˆÔ$Ø.ˆÔØ#6ˆÔ Ø'>ˆÔ$ØˆŒØ!2ˆÔØ"4ˆÔØ ˆŒØ!2ˆÔØ"ˆŒØ.ˆÔØ/NˆÔ,Ø#6ˆÔ ä‰Ñð 	
Ø%Ø%Ø%Ø#9ñ		
ð
 ó	
ó    )iYÄ  i   é   é   i   Úgelui   gš™™™™™¹?ç        r,   é   g{®Gáz”?r,   TFTTé   é    r-   )	Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚattribute_mapr#   Ú__classcell__)r&   s   @r'   r   r      sq   ø„ ñ=ð~ €JØ#4Ð"5Ðà8Ø Ø-ñ€Mð ØØØ "ØØ"Ø #ØØØØ ØØØØØ(,Ø ØØØ÷+/
ñ /
r(   r   N)
r3   Úconfiguration_utilsr   Úutilsr   Ú
get_loggerr0   Úloggerr   Ú__all__r   r(   r'   ú<module>r=      s=   ðñ  å 3Ý ð 
ˆ×	Ñ	˜HÓ	%€ôw
Ð"ô w
ðt ˆ/�r(   