
    fTh!G                         S r SSKJr  SSKJrJrJr  SSKJr  SSK	J
r
  SSKJrJrJr  SSKJr  SS	KJrJrJr  \R*                  " \5      r " S
 S\
5      r " S S\5      rSS/rg)zMBART model configuration    )OrderedDict)AnyMappingOptional   )PreTrainedTokenizer)PretrainedConfig)
OnnxConfigOnnxConfigWithPastOnnxSeq2SeqConfigWithPast) compute_effective_axis_dimension)
TensorTypeis_torch_availableloggingc                   t   ^  \ rS rSrSrSrS/rSSS.r                        S
U 4S jjrS	r	U =r
$ )MBartConfig   a5  
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
```mbartpast_key_valuesencoder_attention_headsd_model)num_attention_headshidden_sizec           	      ,  > Xl         X l        Xl        X@l        X0l        XPl        Xpl        X`l        Xl        Xl	        UU l
        UU l        Xl        UU l        Xl        Xl        UU l        Xl        X0l        UU l        [(        TU ]T  " SUUUUUS.UD6  g )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_cachenum_hidden_layersscale_embeddingsuper__init__)selfr!   r"   r$   r#   r   r&   r%   r'   r-   r.   r0   r   r+   r   r(   r)   r*   r,   r/   r2   r   r   r   r   kwargs	__class__s                             e/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/mbart/configuration_mbart.pyr4   MBartConfig.__init__l   s    8 %'>$.,'>$.,'>$!2"4#6  !2!2"4"!/. 	
%%%1 3	
 	
    )r*   r+   r)   r/   r   r'   r%   r.   r&   r(   r   r#   r-   r$   r,   r"   r1   r2   r0   r!   )iY              r<   r=   r>           r?   TTgelur;   g?r?   r?   g{Gz?r?   F   r      rB   )__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferenceattribute_mapr4   __static_attributes____classcell__r7   s   @r8   r   r      sy    GR J#4"5,EV_`M  $ " ""37
 7
r:   r   c                   ~  ^  \ rS rSr\S\\\\\4   4   4S j5       r\S\\\\\4   4   4U 4S jj5       r	    SS\
S\S\S\S	\\   S\\\4   4S
 jjr    SS\
S\S\S\S	\\   S\\\4   4S jjr    SS\
S\S\S\S	\\   S\\\4   4S jjr    SS\
S\S\S\S	\\   S\\\4   4S jjrU 4S jrSrU =r$ )MBartOnnxConfig   returnc           	      &   U R                   S;   ak  [        SSSS.4SSSS.4/5      nU R                  (       a  SS0US'   SS	S.US
'   OSSS.US'   SSS.US
'   U R                  (       a  U R                  USS9  U$ U R                   S:X  ab  [        SSSS.4SSSS.4/5      nU R                  (       a8  U R                  u  p#[        U5       H  nSSS.USU S3'   SSS.USU S3'   M     U$ [        SSSS.4SSSS.4SSSS.4S
SSS.4/5      nU$ )Ndefaultz
seq2seq-lm	input_idsbatchencoder_sequence)r   rA   attention_maskr   decoder_input_idsz past_decoder_sequence + sequencedecoder_attention_maskdecoder_sequenceinputs)	direction	causal-lmpast_sequence + sequencer   rB   zpast_key_values..key.value)taskr   use_pastfill_with_past_key_values_
num_layersrange)r5   common_inputsnum_encoder_layers_is        r8   r\   MBartOnnxConfig.inputs   s   9911' g2D"EF%77I'JKM }}67\12>EJl:m679@EW5X12>EJ\:]67}}///R0 / YY+%' g2D"EF%77I'JKM }}(,%"12ADKPj@kM$4QCt"<=FMRlBmM$4QCv">? 3  ( g2D"EF%77I'JK(g:L*MN-7?Q/RS	M r:   c                    > U R                   S;   a  [        TU ]  nU$ [        [        U ]
  nU R                  (       a8  U R
                  u  p#[        U5       H  nSSS.USU S3'   SSS.USU S3'   M     U$ )NrS   rV   r_   r`   zpresent.ra   rb   )rc   r3   outputsr   rd   rf   rg   )r5   common_outputsri   rj   rk   r7   s        r8   rn   MBartOnnxConfig.outputs   s    9911"W_N  ##5tDN}}(,%"12A=DIc9dNXaS#56?FKe;fNXaS#78 3 r:   	tokenizer
batch_size
seq_lengthis_pair	frameworkc           	      d   U R                  XX4U5      nU R                  (       d  UOSnU R                  XXtU5      nUR                  5        V	V
s0 s H  u  pSU	 3U
_M     nn	n
[        S0 UDUD6nU R                  (       Ga  [	        5       (       d  [        S5      eSS KnUS   R                  u  pUS   R                  S   nU R                  u  nnUUUU R                  R                  U-  4nUS-   nUUUU R                  R                  U-  4nUR                  US   UR                  UU5      /SS	9US'   / US
'   U R                  u  nn[        UU5      n[        UU5      U-
  nUU:  a  SOSn[!        U5       HW  nUS
   R#                  UR%                  U5      UR%                  U5      UR%                  U5      UR%                  U5      45        MY     US:X  a  UOUn[!        UU5       H7  nUS
   R#                  UR%                  U5      UR%                  U5      45        M9     U$ s  sn
n	f )NrA   decoder_ACannot generate dummy past_keys inputs without PyTorch installed.r   rU   rY   r   rZ   dimr   encoderdecoderr    )I_generate_dummy_inputs_for_sequence_classification_and_question_answeringrd   itemsdictr   
ValueErrortorchshaper   _configr   catonesrf   minmaxrg   appendzeros)r5   rq   rr   rs   rt   ru   encoder_inputsdecoder_seq_lengthdecoder_inputsnametensorrh   r   rV   encoder_seq_lengthnum_encoder_attention_headsnum_decoder_attention_headsencoder_shapedecoder_past_lengthdecoder_shaperi   num_decoder_layersmin_num_layersmax_num_layersremaining_side_namerj   r   s                              r8   1_generate_dummy_inputs_for_default_and_seq2seq_lmAMBartOnnxConfig._generate_dummy_inputs_for_default_and_seq2seq_lm   sp    gg:	

 04}}Z!gg#5	
 IWH\H\H^_H^HTF+V3H^_@~@@===%'' !dee(5k(B(H(H%E!./B!C!I!I!!LGKG_G_D')D+"((,GG	M #5q"8+#((,GG	M 7<ii78%**UL_:`agh 7@ 7M23 02M+,59__2 2 !35GHN !35GH>YN/ADV/V)\e>*/077M2M2M2M2	 + &9I%EM=E>>:/077U9KU[[Y^M_8`a ;c `s   H,c           	         U R                  XX4U5      nU R                  (       a  [        5       (       d  [        S5      eSS KnUS   R
                  u  pU	S-   n
U R                  u  pU R                  u  pUUU
U R                  R                  U-  4nUS   R                  nUR                  US   UR                  XUS9/SS9US'   [        U5       Vs/ s H$  oR                  U5      UR                  U5      4PM&     snUS	'   U$ s  snf )
Nrx   r   rU   rB   rX   )dtyperA   ry   r   )r}   rd   r   r   r   r   rf   r   r   r   r   r   r   rg   r   )r5   rq   rr   rs   rt   ru   rh   r   rV   seqlenpast_key_values_lengthri   rj   r   
past_shape
mask_dtypes                   r8   $_generate_dummy_inputs_for_causal_lm4MBartOnnxConfig._generate_dummy_inputs_for_causal_lm%  s.    ff:	
 ==%'' !dee)+6<<ME%+aZ"$(OO!-1-E-E*'+&((,GG	J ''78>>J.3ii/0%**Ubl*2mntu /8 /M*+ MRRdLe0LeqZ(%++j*ABLe0M+, 0s   +Dc                     [        U[        R                  SS9nUR                  U5      n[        U[        R                  US9nSR                  UR                  /5      U-  /U-  n[        U" XuS95      nU$ )Nr   )fixed_dimensionnum_token_to_add )return_tensors)r   r
   default_fixed_batchnum_special_tokens_to_adddefault_fixed_sequencejoin	unk_tokenr   )	r5   rq   rr   rs   rt   ru   token_to_adddummy_inputrh   s	            r8   r}   YMBartOnnxConfig._generate_dummy_inputs_for_sequence_classification_and_question_answeringK  s     6
(F(FYZ


 !::7C5
(I(I\h


 xx!4!4 56CDzQY{MNr:   c                     U R                   S;   a  U R                  XX4US9nU$ U R                   S:X  a  U R                  XX4US9nU$ U R                  XX4US9nU$ )NrS   )rr   rs   rt   ru   r^   )rc   r   r   r}   )r5   rq   rr   rs   rt   ru   rh   s          r8   generate_dummy_inputs%MBartOnnxConfig.generate_dummy_inputse  s     9911 RRZdm S M  YY+% EEZdm F M 	 !jjZdm k M r:   c                 p   > U R                   S;   a  [        TU ]	  XX45      ng [        [        U ]  XX45      ng )NrS   )rc   r3   _flatten_past_key_values_r   )r5   flattened_outputr   idxtr7   s        r8   r   )MBartOnnxConfig._flatten_past_key_values_}  s<    9911$w@AQY\`$%>_  r:   r    )r   FN)rC   rD   rE   rF   propertyr   strintr\   rn   r   boolr   r   r   r   r   r}   r   r   rK   rL   rM   s   @r8   rO   rO      s   )WS#X%6 67 ) )V 
gc3h&7!78 
 
 *.B&B B 	B
 B J'B 
c	BN *.$&$ $ 	$
 $ J'$ 
c	$R *.&  	
  J' 
c	: *.&  	
  J' 
c	0 r:   rO   N)rG   collectionsr   typingr   r   r    r   configuration_utilsr	   onnxr
   r   r   
onnx.utilsr   utilsr   r   r   
get_loggerrC   loggerr   rO   __all__r    r:   r8   <module>r      sg      # ) ) # 3 M M : < < 
		H	%E
" E
R\/ \~ +
,r:   