
    sg                      b    d Z ddlZddlmZ ddlmZ  ej                  e      Z G d de      Z	y)zMVP model configuration    N   )PretrainedConfig)loggingc                   p     e Zd ZdZdZdgZdddZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )		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
    ```mvppast_key_valuesencoder_attention_headsd_model)num_attention_headshidden_sizec           
         || _         || _        || _        || _        || _        || _        || _        || _        || _        || _	        || _
        || _        || _        || _        |	| _        |
| _        || _        || _        || _        || _        || _        || _        || _        t/        | `  d||||||d| | j2                  H|j5                  dd      r5| j6                  | _        t9        j:                  d| j6                   d       y y y )N)pad_token_idbos_token_ideos_token_idis_encoder_decoderdecoder_start_token_idforced_eos_token_id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. )
vocab_sizemax_position_embeddingsr   encoder_ffn_dimencoder_layersr
   decoder_ffn_dimdecoder_layersdecoder_attention_headsdropoutattention_dropoutactivation_dropoutactivation_functioninit_stdencoder_layerdropdecoder_layerdropclassifier_dropout	use_cachenum_hidden_layersscale_embedding
use_promptprompt_lengthprompt_mid_dimsuper__init__forced_bos_token_idgetr   warningswarn)selfr   r   r   r   r
   r   r   r   r#   r$   r!   r   r   r   r    r"   r%   r(   r&   r   r   r   r   r   r   r)   r*   r+   kwargs	__class__s                                 \/var/www/html/venv/lib/python3.12/site-packages/transformers/models/mvp/configuration_mvp.pyr-   zMvpConfig.__init__m   sA   @ %'>$.,'>$.,'>$!2"4#6  !2!2"4"!/.$*, 	
%%%1#9 3	
 	
 ##+

;\^c0d'+'8'8D$MMLTM^M^L_ `Q Q 1e+    )i[              r8   r9   r:           r;   gelur7   g?r;   r;   g{Gz?r;   FT   r      Tr>   r>   Fd   i   )	__name__
__module____qualname____doc__
model_typekeys_to_ignore_at_inferenceattribute_mapr-   __classcell__)r4   s   @r5   r   r      s    L\ J#4"5,EV_`M  $ " "" ;G Gr6   r   )
rC   r0   configuration_utilsr   utilsr   
get_loggerr@   loggerr   r   r6   r5   <module>rL      s6      3  
		H	%Z  Zr6   