+
    œ°³jw  ã                   óx   € R t ^ 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	# )
zPhi model configuration)Ústrict)ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzmicrosoft/phi-1)Ú
checkpointc                   óî   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	/tRR.R.3RR.R.3RRR.R.3RR.R.3/tRt	Rt
Rt^t^ tRtRtRtRtRtRtRtRtRtRtRtRt^t^tRtV 3R ltV3R ltR tVt V ;t!# )!Ú	PhiConfigaí  
qk_layernorm (`bool`, *optional*, defaults to `False`):
    Whether or not to normalize the Queries and Keys after projecting the hidden states.

Example:

```python
>>> from transformers import PhiModel, PhiConfig

>>> # Initializing a Phi-1 style configuration
>>> configuration = PhiConfig.from_pretrained("microsoft/phi-1")

>>> # Initializing a model from the configuration
>>> model = PhiModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```ÚphiÚpast_key_valueszlayers.*.self_attn.q_projÚcolwisezlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.denseÚrowwisezlayers.*.mlp.fc1zlayers.*.mlp.fc2Úembed_tokensÚ	input_idsÚinputs_embedsÚembed_dropoutÚlayersÚhidden_statesÚattention_maskÚfinal_layernormi È  i   i    Ng        Úgelu_newg{®Gáz”?gñhãˆµøä>TFc                óŠ   <€ V P                   f   V P                  V n         VP                  RR4       \        SV `  ! R/ VB  R # )NÚpartial_rotary_factorg      à?© )Únum_key_value_headsÚnum_attention_headsÚ
setdefaultÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s   &,€Új/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/phi/configuration_phi.pyr   ÚPhiConfig.__post_init__T   s>   ø€ Ø×#Ñ#Ò+Ø'+×'?Ñ'?ˆDÔ$à×ÑÐ1°3Ô7Ü‰ÒÑ' Ô'ó    c                ó¾  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R&   S[S[ ,          ;R&   S[S[ ,          ;R	&   S[S[ ,          R,          ;R
&   S[;R&   S[ ;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[S[,          R,          ;R&   S[;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[ R,          ;R&   # )é   Ú
vocab_sizeÚhidden_sizeÚintermediate_sizeÚnum_hidden_layersr   Nr   Úresid_pdropÚ
embd_pdropÚattention_dropoutÚ
hidden_actÚmax_position_embeddingsÚinitializer_rangeÚlayer_norm_epsÚ	use_cacheÚtie_word_embeddingsÚrope_parametersÚqk_layernormÚbos_token_idÚeos_token_idÚpad_token_id)ÚintÚfloatÚstrÚboolr   ÚdictÚlist)ÚformatÚ__classdict__s   "€r!   Ú__annotate__ÚPhiConfig.__annotate__   se  ø‡ ‚ ñN ÑñO ñP ÑñQ ñR Ñ!ñS ñT ÑñU ñV Ñ!ñW ñX ˜t�Ñ*ñY ñZ ™•Ñ"ñ[ ñ\ ™•Ñ!ñ] ñ^ ™s•{ TÕ)Ñ/ñ_ ñ` Ñ ña ñb !Ñ'ñc ñd Ñ#ñe ñf Ñ ñg ñh Ññi ñj Ñ%ñk ñl $¡dÕ*¨TÕ1Ñ8ñm ñn Ñño ñp ˜•*Ñ ñq ñr ™™S�	•/ DÕ(Ñ,ñs ñt ˜•*Ñ#òu 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_planr&   r'   r(   r)   r   r   r*   r+   r,   r-   r.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r    r?   s   @@r!   r   r      s  ù‡ € ñð& €JØ#4Ð"5Ðà# YØ# YØ# YØ" IØ˜IØ˜IðÐð 	˜+˜¨Ð(9Ð:Ø˜?Ð+¨oÐ->Ð?Ø�OÐ%5Ð6¸Ð8IÐJØ˜_Ð-°Ð/@ÐAð	Ðð €JØ€KØ!ÐØÐØ!ÐØ&*ÐØ"€KØ!€JØ,/ÐØ €JØ#'ÐØ#ÐØ €NØ€IØ %ÐØ48€OØ€LØ €LØ+,€LØ#€Lõ(÷y … r#   r   N)rF   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r   Ú__all__r   r#   r!   Ú<module>rT      sJ   ðñ å .å 3Ý 1Ý #ñ Ð,Ô-Øô?(Ð ó ?(ó ó .ð?(ðD ˆ-‚r#   