ó
    Oëgjò  ã                   ó@   • S SK r S SKJr  S SKJrJr   " S S\\5      rg)é    N)ÚPretrainedConfig)ÚHybridAttentionConfigÚ_HybridAttentionConfigMixinc            F       ó6  ^ • \ rS rSrSrS/r                                  S)S\S\S\S\S-  S	\S-  S
\S\S\S-  S\S-  S\S\	S\S\	S\S-  S\S\S\	S-  S\S\	S\	S\
S\	S\S-  S\S\S\	S\S \	S!\	S"\	S#\	S$\	S%\S&\S-  4DU 4S' jjjrS(rU =r$ )*Ú	GLAConfigé   ÚglaÚpast_key_valuesNÚhidden_sizeÚexpand_kÚexpand_vÚhidden_ratioÚintermediate_sizeÚnum_hidden_layersÚ	num_headsÚnum_kv_headsÚfeature_mapÚ	attn_modeÚuse_short_convÚ	conv_sizeÚuse_output_gateÚ	clamp_minÚ
hidden_actÚmax_position_embeddingsÚelementwise_affineÚnorm_epsÚuse_gkÚuse_gvÚattnÚ	use_cacheÚpad_token_idÚbos_token_idÚeos_token_idÚtie_word_embeddingsÚinitializer_rangeÚ	fuse_normÚfuse_swigluÚfuse_cross_entropyÚfuse_linear_cross_entropyÚ
use_l2warpÚ
vocab_sizeÚattnres_block_sizec#                 óp  >• Xl         X l        X0l        X@l        XPl        X`l        Xpl        X€l        X�l        X l	        X°l
        XÀl        XÐl        Xàl        Xðl        UU l        UU l        UU l        UU l        UU l        UU l        UU l        UU l        UU l        UU l        UU l        UU l        U U l        U!U l        U"U l        U(       a  U(       a  [=        S5      eU(       a  [>        R@                  " S5        U"b$  U"S:w  a  U"S:  d	  U"S-  S:w  a  [=        SU" S35      e[B        T$U ]ˆ  " S	UUUUS.U#D6  g )
NzU`fuse_cross_entropy` and `fuse_linear_cross_entropy` cannot be True at the same time.zÅ`fuse_linear_cross_entropy` is enabled, which can improves memory efficiency at the potential cost of reduced precision. If you observe issues like loss divergence, consider disabling this setting.é   é   r   z�`attnres_block_size` must be `None`, `1` (full mode), or an even integer (one block contains `attnres_block_size // 2` transformer layers); got Ú.)r!   r"   r#   r$   © )#r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r    r%   r&   r'   r(   r)   r*   r+   r,   Ú
ValueErrorÚwarningsÚwarnÚsuperÚ__init__)%Úselfr   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r    r!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   r,   ÚkwargsÚ	__class__s%                                       €Ú®C:\Users\johnn\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\LocalCache\local-packages\Python313\site-packages\fla/models/gla/configuration_gla.pyr6   ÚGLAConfig.__init__   sg  ø€ ðL 'ÔØ ŒØ ŒØ(ÔØ!2ÔØ!2ÔØ"ŒØ(ÔØ&ÔØ"ŒØ,ÔØ"ŒØ.ÔØ"ŒØ$ŒØ'>ˆÔ$Ø"4ˆÔØ ˆŒØˆŒØˆŒØˆŒ	Ø"ˆŒØ!2ˆÔà"ˆŒØ&ˆÔØ"4ˆÔØ)BˆÔ&Ø$ˆŒØ$ˆŒØ"4ˆÔæÖ";ÜØgóð ö %Ü�MŠMð_ôð Ñ)Ð.@ÀAÓ.EØ! AÓ%Ð);¸aÑ)?À1Ó)DÜ ðSØSeÐRfÐfgðióð ô
 	‰Òð 	
Ø%Ø%Ø%Ø 3ñ		
ð
 ó	
ó    )r   r   r,   r   r   r   r   r   r   r(   r)   r&   r'   r   r   r   r%   r   r   r   r   r   r   r    r   r   r*   r   r   r+   )"é   g      à?g      ð?é   Né   r>   NNÚchunkFr>   TNÚswishr=   Tg�íµ ÷Æ°>TFNTNr.   r/   Fg{®Gáz”?TTTFFi }  N)Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú
model_typeÚkeys_to_ignore_at_inferenceÚintÚfloatÚstrÚboolr   r6   Ú__static_attributes__Ú__classcell__)r9   s   @r:   r   r      s"  ø† à€JØ#4Ð"5Ðð  ØØØ#$Ø(,Ø!#ØØ#'Ø"&Ø Ø$ØØ $Ø"&Ø!Ø'+Ø*.ØØØØ&*ØØ#'ØØØ$)Ø#'ØØ Ø#'Ø*/Ø ØØ)-ñG^
àð^
ð ð^
ð ð	^
ð
 ˜D‘jð^
ð  ™:ð^
ð ð^
ð ð^
ð ˜D‘jð^
ð ˜4‘Zð^
ð ð^
ð ð^
ð ð^
ð ð^
ð ˜4‘<ð^
ð  ð!^
ð" "%ð#^
ð$ ! 4™Kð%^
ð& ð'^
ð( ð)^
ð* ð+^
ð, $ð-^
ð. ð/^
ð0 ˜D‘jð1^
ð2 ð3^
ð4 ð5^
ð6 "ð7^
ð8 !ð9^
ð: ð;^
ð< ð=^
ð> !ð?^
ð@ $(ðA^
ðB ðC^
ðD ðE^
ðF   $™J÷G^
ö ^
r<   r   )r3   Ú transformers.configuration_utilsr   Úfla.models.hybridr   r   r   r1   r<   r:   Ú<module>rP      s"   ðó å =ç Pôc
Ð+Ð-=õ c
r<   