ó
    qyüi›  ã                   ód   • 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 configurationé    )Ústricté   )ÚPreTrainedConfig)Úauto_docstringz"microsoft/prophetnet-large-uncased)Ú
checkpointc                   ó&  • \ 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!)8ÚProphetNetConfigé   aÚ  
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.
Ú
prophetnetÚpast_key_valuesÚnum_attention_headsÚnum_encoder_attention_headsgš™™™™™¹?Úactivation_dropoutÚgeluÚactivation_functioni:w  Ú
vocab_sizei   Úhidden_sizei   Úencoder_ffn_dimé   Únum_encoder_layersé   Údecoder_ffn_dimÚnum_decoder_layersÚnum_decoder_attention_headsÚattention_dropoutÚdropouti   Úmax_position_embeddingsg{®Gáz”?Úinit_stdTÚis_encoder_decoderÚadd_cross_attentionr   NÚdecoder_start_token_idé   Úngramé    Únum_bucketsé€   Úrelative_max_distanceFÚdisable_ngram_lossg        ÚepsÚ	use_cacheÚpad_token_idé   Úbos_token_idÚeos_token_idÚ
is_decoderÚtie_word_embeddingsÚreturnc                 ó   • U R                   $ )N)r   )Úselfs    Út/home/mande/repo/quber/.venv/lib/python3.13/site-packages/transformers/models/prophetnet/configuration_prophetnet.pyÚnum_hidden_layersÚ"ProphetNetConfig.num_hidden_layersM   s   € à×&Ñ&Ð&ó    c                 ó   • [        S5      e)NzyThis model does not support the setting of `num_hidden_layers`. Please set `num_encoder_layers` and `num_decoder_layers`.)ÚNotImplementedError)r3   Úvalues     r4   r5   r6   Q   s   € ä!ð%ó
ð 	
r7   © ).Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚattribute_mapr   ÚfloatÚintÚ__annotations__r   Ústrr   r   r   r   r   r   r   r   r   r   r   r   r   Úboolr    r!   r#   r%   r'   r(   r)   r*   r+   r-   r.   Úlistr/   r0   Úpropertyr5   ÚsetterÚ__static_attributes__r;   r7   r4   r	   r	      s£  ‡ ñð" €JØ#4Ð"5ÐàÐ<ð€Mð '*Ð˜ ™Ó)Ø%Ð˜Ó%Ø€J�ÓØ€K�ÓØ€O�SÓØ Ð˜Ó Ø')Ð Ó)Ø€O�SÓØ Ð˜Ó Ø')Ð Ó)Ø%(Ð�u˜s‘{Ó(Ø€GˆU�S‰[ÓØ#&Ð˜SÓ&Ø€HˆeÓØ#Ð˜Ó#Ø $Ð˜Ó$Ø)*Ð˜C $™JÓ*Ø€Eˆ3ƒNØ€K�ÓØ!$Ð˜3Ó$Ø$Ð˜Ó$Ø€CˆÓØ€IˆtÓØ €L�#˜‘*Ó Ø €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø€J�ÓØ $Ð˜Ó$àð' 3ó 'ó ð'ð ×Ññ
ó ó
r7   r	   N)	r@   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r	   Ú__all__r;   r7   r4   Ú<module>rQ      sI   ðñ %å .å 3Ý #ñ Ð?Ñ@Øô>
Ð'ó >
ó ó Að>
ðB Ð
�r7   