o
    Zh!G                     @   s   d Z ddlmZ ddlmZmZmZ ddlmZ ddl	m
Z
 ddlmZmZmZ ddlmZ dd	lmZmZmZ eeZG d
d de
ZG dd deZddgZdS )zMBART model configuration    )OrderedDict)AnyMappingOptional   )PreTrainedTokenizer)PretrainedConfig)
OnnxConfigOnnxConfigWithPastOnnxSeq2SeqConfigWithPast) compute_effective_axis_dimension)
TensorTypeis_torch_availableloggingc                       sf   e Zd ZdZdZdgZdddZ					
				
																	d fdd	Z  ZS )MBartConfiga1  
    This is the configuration class to store the configuration of a [`MBartModel`]. It is used to instantiate an MBART
    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 MBART
    [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) 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 MBART model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`MBartModel`] or [`TFMBartModel`].
        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`.

    Example:

    ```python
    >>> from transformers import MBartConfig, MBartModel

    >>> # Initializing a MBART facebook/mbart-large-cc25 style configuration
    >>> configuration = MBartConfig()

    >>> # Initializing a model (with random weights) from the facebook/mbart-large-cc25 style configuration
    >>> model = MBartModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```Zmbartpast_key_valuesencoder_attention_headsd_model)num_attention_headshidden_sizeY                      Tgelu皙?{Gz?F   r      c                    s   || _ || _|| _|| _|| _|| _|| _|| _|| _|| _	|| _
|| _|| _|| _|	| _|
| _|| _|| _|| _|| _t jd|||||d| d S )N)pad_token_idbos_token_ideos_token_idis_encoder_decoderforced_eos_token_id )
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_cacheZnum_hidden_layersscale_embeddingsuper__init__)selfr'   r(   r*   r)   r   r,   r+   r-   r3   r4   r6   r$   r1   r   r.   r/   r0   r2   r5   r7   r!   r"   r#   r%   kwargs	__class__r&   \/var/www/auris/lib/python3.10/site-packages/transformers/models/mbart/configuration_mbart.pyr9   l   s:   
zMBartConfig.__init__)r   r   r   r   r   r   r   r   r   r   TTr   r   r   r   r   r   r   Fr   r   r    r    )	__name__
__module____qualname____doc__Z
model_typeZkeys_to_ignore_at_inferenceZattribute_mapr9   __classcell__r&   r&   r<   r>   r      s<    I
r   c                       sD  e Zd Zedeeeeef f fddZedeeeeef f f fddZ				dd	e	d
edede
dee deeef fddZ				dd	e	d
edede
dee deeef fddZ				dd	e	d
edede
dee deeef fddZ				dd	e	d
edede
dee deeef fddZ fddZ  ZS )MBartOnnxConfigreturnc                 C   s4  | j dv r@tddddfddddfg}| jr&ddi|d< dd	d|d
< nddd|d< ddd|d
< | jr>| j|dd |S | j dkr|tddddfddddfg}| jrz| j\}}t|D ]}ddd|d| d< ddd|d| d< qa|S tddddfddddfddddfd
dddfg}|S )Ndefaultz
seq2seq-lm	input_idsbatchZencoder_sequence)r   r   attention_maskr   decoder_input_idsz past_decoder_sequence + sequencedecoder_attention_maskZdecoder_sequenceinputs)	direction	causal-lmpast_sequence + sequencer   r    zpast_key_values..key.value)taskr   use_pastZfill_with_past_key_values_
num_layersrange)r:   common_inputsnum_encoder_layers_ir&   r&   r>   rM      sD   


	zMBartOnnxConfig.inputsc                    sp   | j dv rt j}|S tt| j}| jr6| j\}}t|D ]}ddd|d| d< ddd|d| d< q|S )NrF   rI   rP   rQ   zpresent.rR   rS   )rT   r8   outputsr
   rU   rV   rW   )r:   Zcommon_outputsrY   rZ   r[   r<   r&   r>   r\      s   

zMBartOnnxConfig.outputsFN	tokenizer
batch_size
seq_lengthis_pair	frameworkc              	   C   s  |  |||||}| js|nd}|  |||||}dd | D }tdi ||}	| jrt s5tddd l}
|	d j\}}|	d jd }| j\}}|||| j	j
| f}|d }|||| j	j
| f}|
j|	d	 |
||gdd
|	d	< g |	d< | j\}}t||}t||| }||krdnd}t|D ]}|	d |
||
||
||
|f q|dkr|n|}t||D ]}|	d |
||
|f q|	S )Nr   c                 S   s   i | ]
\}}d | |qS )Zdecoder_r&   ).0nameZtensorr&   r&   r>   
<dictcomp>   s    zUMBartOnnxConfig._generate_dummy_inputs_for_default_and_seq2seq_lm.<locals>.<dictcomp>ACannot generate dummy past_keys inputs without PyTorch installed.r   rH   rK   r   rL   dimr   encoderdecoderr&   )I_generate_dummy_inputs_for_sequence_classification_and_question_answeringrU   itemsdictr   
ValueErrortorchshaper   _configr   catonesrV   minmaxrW   appendzeros)r:   r^   r_   r`   ra   rb   Zencoder_inputsZdecoder_seq_lengthZdecoder_inputsrX   ro   rI   Zencoder_seq_lengthnum_encoder_attention_headsZnum_decoder_attention_headsZencoder_shapeZdecoder_past_lengthZdecoder_shaperY   Znum_decoder_layersZmin_num_layersZmax_num_layersZremaining_side_namerZ   rp   r&   r&   r>   1_generate_dummy_inputs_for_default_and_seq2seq_lm   s^   







	 zAMBartOnnxConfig._generate_dummy_inputs_for_default_and_seq2seq_lmc                    s   |  |||||}| jr\t stddd l|d j\}}|d }	| j\}
}| j\}}|||	| jj	| f |d j
}j|d j||	|dgdd|d<  fd	d
t|
D |d< |S )Nrf   r   rH   r    rJ   )dtyper   rg   c                    s    g | ]}    fqS r&   )rw   )rc   rZ   Z
past_shapero   r&   r>   
<listcomp>F  s    zHMBartOnnxConfig._generate_dummy_inputs_for_causal_lm.<locals>.<listcomp>r   )rk   rU   r   rn   ro   rp   rV   r   rq   r   rz   rr   rs   rW   )r:   r^   r_   r`   ra   rb   rX   rI   ZseqlenZpast_key_values_lengthrY   rZ   rx   Z
mask_dtyper&   r{   r>   $_generate_dummy_inputs_for_causal_lm%  s0   






z4MBartOnnxConfig._generate_dummy_inputs_for_causal_lmc           	      C   sV   t |tjdd}||}t |tj|d}d|jg| g| }t|||d}|S )Nr   )Zfixed_dimensionZnum_token_to_add )Zreturn_tensors)r   r	   Zdefault_fixed_batchZnum_special_tokens_to_addZdefault_fixed_sequencejoinZ	unk_tokenrm   )	r:   r^   r_   r`   ra   rb   Ztoken_to_addZdummy_inputrX   r&   r&   r>   rk   K  s   
zYMBartOnnxConfig._generate_dummy_inputs_for_sequence_classification_and_question_answeringc                 C   s\   | j dv r| j|||||d}|S | j dkr"| j|||||d}|S | j|||||d}|S )NrF   )r_   r`   ra   rb   rO   )rT   ry   r}   rk   )r:   r^   r_   r`   ra   rb   rX   r&   r&   r>   generate_dummy_inputse  s   




z%MBartOnnxConfig.generate_dummy_inputsc                    s:   | j dv rt ||||}d S tt| ||||}d S )NrF   )rT   r8   _flatten_past_key_values_r   )r:   Zflattened_outputrd   idxtr<   r&   r>   r   }  s
   

z)MBartOnnxConfig._flatten_past_key_values_)r]   r]   FN)r?   r@   rA   propertyr   strintrM   r\   r   boolr   r   r   ry   r}   rk   r   r   rC   r&   r&   r<   r>   rD      s     +$

G

)



rD   N)rB   collectionsr   typingr   r   r    r   Zconfiguration_utilsr   Zonnxr	   r
   r   Z
onnx.utilsr   utilsr   r   r   Z
get_loggerr?   loggerr   rD   __all__r&   r&   r&   r>   <module>   s   
 
 `