+
    œ°³jm  ã                   ót   € ^ RI H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	# )
é    )Ústrict)ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzgoogle/gemma2-7b)Ú
checkpointc                   ó   a a€ ] tR t^t oRtRtR.tRRRRRRRR	R
RRRRR	/tRR.R.3RRR.R.3RR.R.3/tRt	Rt
Rt^t^t^tRtRtRtRtRtRt^ t^t^tRtRtRtRtRtR tRtR!tR"t Rt!V 3R# lt"R$ t#V3R% lt$R&t%Vt&V ;t'# )'ÚGemma2ConfigaX  
query_pre_attn_scalar (`float`, *optional*, defaults to 256):
    scaling factor used on the attention scores
final_logit_softcapping (`float`, *optional*, defaults to 30.0):
    scaling factor when applying tanh softcapping on the logits.
attn_logit_softcapping (`float`, *optional*, defaults to 50.0):
    scaling factor when applying tanh softcapping on the attention scores.
use_bidirectional_attention (`bool`, *optional*):
    If True, the model will attend to all text tokens instead of using a causal mask.

```python
>>> from transformers import Gemma2Model, Gemma2Config
>>> # Initializing a Gemma2 gemma2-7b style configuration
>>> configuration = Gemma2Config()
>>> # Initializing a model from the gemma2-7b style configuration
>>> model = Gemma2Model(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```Úgemma2Úpast_key_valueszlayers.*.self_attn.q_projÚcolwisezlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projÚrowwisezlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projÚembed_tokensÚ	input_idsÚinputs_embedsÚlayersÚhidden_statesÚattention_maskÚnormi è i 	  i $  é   Úgelu_pytorch_tanhi    g{®Gáz”?g�íµ ÷Æ°>TNFg        i   g      >@g      I@c                óä   <€ V P                   fL   \        V P                  4       Uu. uF&  p\        V^,           ^,          4      '       d   RMRNK(  	  upV n         \        SV `  ! R/ VB  R # u upi )NÚsliding_attentionÚfull_attention© )Úlayer_typesÚrangeÚnum_hidden_layersÚboolÚsuperÚ__post_init__)ÚselfÚkwargsÚiÚ	__class__s   &, €Úp/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/gemma2/configuration_gemma2.pyr    ÚGemma2Config.__post_init__^   si   ø€ Ø×ÑÒ#äX]Ð^b×^tÑ^tÔXuó ÙXuÐST¤t¨Q°­U°a­K×'8Ò'8Ñ#Ð>NÒNÑXuñ ˆDÔô 	‰ÒÑ' Ô'ùò	 s   §,A-c                ó–   € V P                   V P                  ,          ^ 8w  d'   \        RV P                    RV P                   R24      hR# )zOPart of `@strict`-powered validation. Validates the architecture of the config.zThe hidden size (z6) is not a multiple of the number of attention heads (z).N)Úhidden_sizeÚnum_attention_headsÚ
ValueError)r!   s   &r%   Úvalidate_architectureÚ"Gemma2Config.validate_architecturef   sS   € à×Ñ˜d×6Ñ6Õ6¸!Ô;ÜØ# D×$4Ñ$4Ð#5ð 6Ø×2Ñ2Ð3°2ð7óð ñ <ó    c                ó"  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[;R&   S[ ;R	&   S[;R
&   S[;R&   S[;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[ R,          ;R&   S[;R&   S[S[,          R,          ;R&   S[;R&   S[ S[,          R,          ;R&   S[ ;R&   S[ R,          ;R&   S[S[,          R,          ;R&   S[R,          ;R&   S[R,          ;R&   S[R,          ;R&   # )é   Ú
vocab_sizer(   Úintermediate_sizer   r)   Únum_key_value_headsÚhead_dimÚhidden_activationÚmax_position_embeddingsÚinitializer_rangeÚrms_norm_epsÚ	use_cacheNÚpad_token_idÚeos_token_idÚbos_token_idÚtie_word_embeddingsÚrope_parametersÚattention_biasÚattention_dropoutÚquery_pre_attn_scalarÚsliding_windowr   Úfinal_logit_softcappingÚattn_logit_softcappingÚuse_bidirectional_attention)ÚintÚstrÚfloatr   Úlistr   Údict)ÚformatÚ__classdict__s   "€r%   Ú__annotate__ÚGemma2Config.__annotate__   s½  ø‡ ‚ ñP ÑñQ ñR ÑñS ñT Ñ!ñU ñV ÑñW ñX Ñ ñY ñZ Ñ ñ[ ñ\ Ññ] ñ^ Ñ0ñ_ ñ` !Ñ'ña ñb Ñ#ñc ñd Ññe ñf Ññg ñh ˜•*Ñ ñi ñj ™™S�	•/ DÕ(Ñ,ñk ñl ˜•*Ñ ñm ñn Ñ$ño ñp $¡dÕ*¨TÕ1Ñ8ñq ñr Ñ ñs ñt ™U•{ TÕ)Ñ/ñu ñv Ñ$ñw ñx ˜$•JÑ%ñy ñz ‘c•˜TÕ!Ñ(ñ{ ñ| # T�\Ñ0ñ} ñ~ " D�LÑ/ñ ñ@ "&¨¥Ñ3òA r-   )r   )(Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planr0   r(   r1   r   r)   r2   r3   r4   r5   r6   r7   r8   r9   r:   r;   r<   r=   r>   r?   r@   rA   r   rB   rC   rD   r    r+   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r$   rK   s   @@r%   r	   r	      s  ù‡ € ñð( €JØ#4Ð"5Ðà# YØ# YØ# YØ# YØ  )Ø 	Ø  )ðÐð 	˜+˜¨Ð(9Ð:Ø�OÐ%5Ð6¸Ð8IÐJØ�/Ð" _Ð$5Ð6ðÐð €JØ€KØ!ÐØÐØ ÐØ ÐØ€HØ0ÐØ#'ÐØ#ÐØ€LØ€IØ €LØ+,€LØ €LØ $ÐØ48€OØ €NØ,/ÐØ!$ÐØ!%€NØ$(€KØ,0ÐØ+/ÐØ/3Ðõ(ò÷U … r-   r	   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r	   Ú__all__r   r-   r%   Ú<module>r`      sK   ðõ* /å 3Ý 1Ý #ñ Ð-Ô.ØôNÐ#ó Nó ó /ðNðb Ð
‚r-   