
    Z j                     d    S r SSKJr  SSKJr  SSKJr  \" SS9\ " S S	\5      5       5       rS	/rg
)zProphetNet model configuration    )strict   )PreTrainedConfig)auto_docstringz"microsoft/prophetnet-large-uncased)
checkpointc                   &   \ rS rSr% SrSrS/rSS0rSr\	\
-  \S'   S	r\\S
'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\	\
-  \S'   Sr\	\
-  \S'   Sr\
\S'   Sr\	\S'   Sr\\S'   Sr\\S'   S r\
S!-  \S"'   S#r\
\S$'   S%r\
\S&'   S'r \
\S('   S)r!\\S*'   S+r"\	\S,'   Sr#\\S-'   S r$\
S!-  \S.'   S/r%\
S!-  \S0'   S#r&\
\'\
   -  S!-  \S1'   S)r(\\S2'   Sr)\\S3'   \*S4\
4S5 j5       r+\+RX                  S6 5       r+S7r-g!)8ProphetNetConfig   a  
ngram (`int`, *optional*, defaults to 2):
    Number of future tokens to predict. Set to 1 to be same as traditional Language model to predict next first
    token.
num_buckets (`int`, *optional*, defaults to 32):
    The number of buckets to use for each attention layer. This is for relative position calculation. See the
    [T5 paper](see https://huggingface.co/papers/1910.10683) for more details.
relative_max_distance (`int`, *optional*, defaults to 128):
    Relative distances greater than this number will be put into the last same bucket. This is for relative
    position calculation. See the [T5 paper](see https://huggingface.co/papers/1910.10683) for more details.
disable_ngram_loss (`bool`, *optional*, defaults to `False`):
    Whether be trained predicting only the next first token.
eps (`float`, *optional*, defaults to 0.0):
    Controls the `epsilon` parameter value for label smoothing in the loss calculation. If set to 0, no label
    smoothing is performed.

prophetnetpast_key_valuesnum_attention_headsnum_encoder_attention_headsg?activation_dropoutgeluactivation_functioni:w  
vocab_sizei   hidden_sizei   encoder_ffn_dim   num_encoder_layers   decoder_ffn_dimnum_decoder_layersnum_decoder_attention_headsattention_dropoutdropouti   max_position_embeddingsg{Gz?init_stdTis_encoder_decoderadd_cross_attentionr   Ndecoder_start_token_id   ngram    num_buckets   relative_max_distanceFdisable_ngram_lossg        eps	use_cachepad_token_id   bos_token_ideos_token_id
is_decodertie_word_embeddingsreturnc                     U R                   $ )N)r   )selfs    ڈ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/prophetnet/configuration_prophetnet.pynum_hidden_layers"ProphetNetConfig.num_hidden_layersM   s    &&&    c                     [        S5      e)NzyThis model does not support the setting of `num_hidden_layers`. Please set `num_encoder_layers` and `num_decoder_layers`.)NotImplementedError)r3   values     r4   r5   r6   Q   s    !%
 	
r7    ).__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferenceattribute_mapr   floatint__annotations__r   strr   r   r   r   r   r   r   r   r   r   r   r   r   boolr    r!   r#   r%   r'   r(   r)   r*   r+   r-   r.   listr/   r0   propertyr5   setter__static_attributes__r;   r7   r4   r	   r	      s   " J#4"5<M '*)%%JKOS  '))OS  '))%(us{(GUS[#&S&He## $$)*C$J*E3NK!$3$$$CIt L#*  L#* +,L#S	/D(,J $$'3 ' ' 
 
r7   r	   N)	r@   huggingface_hub.dataclassesr   configuration_utilsr   utilsr   r	   __all__r;   r7   r4   <module>rQ      sI    % . 3 # ?@>
' >
  A>
B 
r7   