U
    ,È-eU!  ã                   @   sJ   d Z ddlZddlmZ ddlmZ e e¡ZddiZ	G dd	„ d	eƒZ
dS )
z MVP model configurationé    Né   )ÚPretrainedConfig)ÚloggingzRUCAIBox/mvpz<https://huggingface.co/RUCAIBox/mvp/resolve/main/config.jsonc                       s6   e Zd ZdZdZdgZdddœZd‡ fdd„	Z‡  ZS )Ú	MvpConfiga  
    This is the configuration class to store the configuration of a [`MvpModel`]. It is used to instantiate a MVP 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 MVP [RUCAIBox/mvp](https://huggingface.co/RUCAIBox/mvp)
    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 50267):
            Vocabulary size of the MVP model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`MvpModel`].
        d_model (`int`, *optional*, defaults to 1024):
            Dimensionality of the layers and the pooler layer.
        encoder_layers (`int`, *optional*, defaults to 12):
            Number of encoder layers.
        decoder_layers (`int`, *optional*, defaults to 12):
            Number of decoder layers.
        encoder_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer encoder.
        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.
        encoder_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 encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"silu"` and `"gelu_new"` are supported.
        dropout (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, 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.
        classifier_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for classifier.
        max_position_embeddings (`int`, *optional*, defaults to 1024):
            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).
        init_std (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        encoder_layerdrop (`float`, *optional*, defaults to 0.0):
            The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
            for more details.
        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.
        scale_embedding (`bool`, *optional*, defaults to `False`):
            Scale embeddings by diving by sqrt(d_model).
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        forced_eos_token_id (`int`, *optional*, defaults to 2):
            The id of the token to force as the last generated token when `max_length` is reached. Usually set to
            `eos_token_id`.
        use_prompt (`bool`, *optional*, defaults to `False`):
            Whether or not to use prompt.
        prompt_length (`int`, *optional*, defaults to 100):
            The length of prompt.
        prompt_mid_dim (`int`, *optional*, defaults to 800):
            Dimensionality of the "intermediate" layer in prompt.
    Example:

    ```python
    >>> from transformers import MvpConfig, MvpModel

    >>> # Initializing a MVP RUCAIBox/mvp style configuration
    >>> configuration = MvpConfig()

    >>> # Initializing a model (with random weights) from the RUCAIBox/mvp style configuration
    >>> model = MvpModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```ZmvpZpast_key_valuesÚencoder_attention_headsÚd_model)Znum_attention_headsZhidden_sizeé[Ä  é   é   é   é   ç        Úgeluçš™™™™™¹?ç{®Gáz”?FTé   r   é   éd   é   c              	      sà   || _ || _|| _|| _|| _|| _|| _|| _|| _|| _	|| _
|| _|| _|| _|	| _|
| _|| _|| _|| _|| _|| _|| _|| _tƒ jf ||||||dœ|—Ž | jd krÜ| dd¡rÜ| j| _t d| j› d¡ d S )N)Úpad_token_idÚbos_token_idÚeos_token_idÚis_encoder_decoderÚdecoder_start_token_idÚforced_eos_token_idZforce_bos_token_to_be_generatedFz:Please make sure the config includes `forced_bos_token_id=zT` in future versions. The config can simply be saved and uploaded again to be fixed.)Ú
vocab_sizeÚmax_position_embeddingsr   Úencoder_ffn_dimÚencoder_layersr   Údecoder_ffn_dimÚdecoder_layersÚdecoder_attention_headsÚdropoutÚattention_dropoutÚactivation_dropoutÚactivation_functionÚinit_stdÚencoder_layerdropÚdecoder_layerdropÚclassifier_dropoutÚ	use_cacheZnum_hidden_layersÚscale_embeddingÚ
use_promptÚprompt_lengthÚprompt_mid_dimÚsuperÚ__init__Zforced_bos_token_idÚgetr   ÚwarningsÚwarn)Úselfr   r   r   r   r   r    r   r!   r'   r(   r%   r   r"   r#   r$   r&   r)   r+   r*   r   r   r   r   r   r   r,   r-   r.   Úkwargs©Ú	__class__© új/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/mvp/configuration_mvp.pyr0   o   sL     úù
ÿzMvpConfig.__init__)r   r	   r
   r   r   r
   r   r   r   r   r   r	   r   r   r   r   r   FTr   r   r   Tr   r   Fr   r   )	Ú__name__Ú
__module__Ú__qualname__Ú__doc__Z
model_typeZkeys_to_ignore_at_inferenceZattribute_mapr0   Ú__classcell__r8   r8   r6   r9   r      sB   M
                            ãr   )r=   r2   Zconfiguration_utilsr   Úutilsr   Z
get_loggerr:   ÚloggerZ!MVP_PRETRAINED_CONFIG_ARCHIVE_MAPr   r8   r8   r8   r9   Ú<module>   s   
 ÿ