+
    œ°³j›  ã                   ól   € R t ^ RIHt ^RIHt ^RIHt ]! RR7      ] ! R R]4      4       4       tR.tR# )	zProphetNet model configuration)Ústrict)ÚPreTrainedConfig)Úauto_docstringz"microsoft/prophetnet-large-uncased)Ú
checkpointc                   óò   a € ] tR t^t o RtRtR.tRR/tRtRt	Rt
R	tR
t^t^tR
t^t^tRtRtRtRtRtRt^ t^t^ t^€tRtRtRt^ t^t ^t!Rt"Rt#]$V 3R lR l4       t%]%PL                  R 4       t%V 3R lt'Rt(V t)R# )ÚProphetNetConfigaÚ  
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gelui:w  i   i   i   g{®Gáz”?TFg        c                ó    <€ V ^8„  d   QhRS[ /# )é   Úreturn)Úint)ÚformatÚ__classdict__s   "€Úx/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/prophetnet/configuration_prophetnet.pyÚ__annotate__ÚProphetNetConfig.__annotate__N   s   ø€ ÷ 'ñ '¡3ñ 'ó    c                ó   € V P                   # )N)Únum_encoder_layers)Úselfs   &r   Únum_hidden_layersÚ"ProphetNetConfig.num_hidden_layersM   s   € à×&Ñ&Ð&r   c                ó   € \        R 4      h)zyThis model does not support the setting of `num_hidden_layers`. Please set `num_encoder_layers` and `num_decoder_layers`.)ÚNotImplementedError)r   Úvalues   &&r   r   r   Q   s   € ä!ð%ó
ð 	
r   c                óò  <€ V ^8„  d   Qh/ S[ S[,          ;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[;R	&   S[;R
&   S[ S[,          ;R&   S[ S[,          ;R&   S[;R&   S[ ;R&   S[;R&   S[;R&   S[R,          ;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[ ;R&   S[;R&   S[R,          ;R&   S[R,          ;R&   S[S[S[,          ,          R,          ;R&   S[;R&   S[;R&   # )r   Úactivation_dropoutÚactivation_functionÚ
vocab_sizeÚhidden_sizeÚencoder_ffn_dimr   r   Údecoder_ffn_dimÚnum_decoder_layersÚnum_decoder_attention_headsÚattention_dropoutÚdropoutÚmax_position_embeddingsÚinit_stdÚis_encoder_decoderÚadd_cross_attentionNÚdecoder_start_token_idÚngramÚnum_bucketsÚrelative_max_distanceÚdisable_ngram_lossÚepsÚ	use_cacheÚpad_token_idÚbos_token_idÚeos_token_idÚ
is_decoderÚtie_word_embeddings)Úfloatr   ÚstrÚboolÚlist)r   r   s   "€r   r   r      sÁ  ø‡ ‚ ñ4 ¡�Ñ)ñ5 ñ6 Ñ%ñ7 ñ8 Ññ9 ñ: Ññ; ñ< Ññ= ñ> Ñ ñ? ñ@ "%Ñ)ñA ñB ÑñC ñD Ñ ñE ñF "%Ñ)ñG ñH ™s•{Ñ(ñI ñJ ‘S�[ÑñK ñL !Ñ&ñM ñN ÑñO ñP Ñ#ñQ ñR Ñ$ñS ñT   $�JÑ*ñU ñV �NñW ñX ÑñY ñZ Ñ$ñ[ ñ\ Ñ$ñ] ñ^ 
Ññ_ ñ` Ñña ñb ˜•*Ñ ñc ñd ˜•*Ñ ñe ñf ™™S�	•/ DÕ(Ñ,ñg ñh Ññi ñj Ñ$òk r   © N)*Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚattribute_mapr    r!   r"   r#   r$   r   r   r%   r&   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r8   r9   Úpropertyr   ÚsetterÚ__annotate_func__Ú__static_attributes__Ú__classdictcell__)r   s   @r   r   r      s÷   ø‡ € ñð" €JØ#4Ð"5ÐàÐ<ð€Mð '*ÐØ%ÐØ€JØ€KØ€OØ ÐØ')ÐØ€OØ ÐØ')ÐØ%(ÐØ€GØ#&ÐØ€HØ#ÐØ $ÐØ)*ÐØ€EØ€KØ!$ÐØ$ÐØ€CØ€IØ €LØ €LØ+,€LØ€JØ $Ðà÷'ó ð'ð ×Ññ
ó ð
÷y ƒ r   r   N)	rC   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r   Ú__all__r>   r   r   Ú<module>rP      sI   ðñ %å .å 3Ý #ñ Ð?Ô@Øô>
Ð'ó >
ó ó Að>
ðB Ð
‚r   