+
    œ°³jÃ  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,naver-hyperclovax/HyperCLOVAX-SEED-Think-14B)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RtRtRtR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!V 3R  lt"R! t#V3R" lt$R#t%Vt&V ;t'# )$ÚHyperCLOVAXConfigaÜ  
embedding_multiplier (`float`, *optional*, defaults to `1.0`):
    Scaling factor applied to the token embedding outputs. Used in MuP to control the
    scale of the embedding activations.
logits_scaling (`float`, *optional*, defaults to `1.0`):
    Scaling factor **multiplied** to the final logits before loss computation or sampling.
    Used in MuP to ensure consistent output scale across model sizes. Note: unlike
    [`GraniteConfig`], this is a multiplier, not a divisor.
residual_multiplier (`float`, *optional*, defaults to `1.0`):
    Scaling factor applied to each sub-layer output before adding to the residual stream.
    Used in Maximal Update Parametrization (MuP) to stabilize training across model sizes.
attention_multiplier (`float`, *optional*, defaults to `head_dim ** -0.5`):
    Scaling factor applied to attention logits before softmax, replacing the standard
    `1 / sqrt(head_dim)` scaling. Set explicitly for MuP-based training; when `None`,
    defaults to the standard value.
use_post_norm (`bool`, *optional*, defaults to `True`):
    Whether to apply an extra RMSNorm after each sub-layer output (Peri-Layer Normalization).

```python
>>> from transformers import HyperCLOVAXModel, HyperCLOVAXConfig

>>> # Initializing a HyperCLOVAX style configuration
>>> configuration = HyperCLOVAXConfig()

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

>>> # Accessing the model configuration
>>> configuration = model.config
```ÚhyperclovaxÚ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 }  i   i +  NÚsilui   g{®Gáz”?g�íµ ÷Æ°>TFg        g      ð?c                ó  <€ V P                   f#   V P                  V P                  ,          V n         V P                  f   V P                  V n        \        SV `  ! R/ VB  V P                  f   V P                   R,          V n        R # R # )N© g      à¿)Úhead_dimÚhidden_sizeÚnum_attention_headsÚnum_key_value_headsÚsuperÚ__post_init__Úattention_multiplier)ÚselfÚkwargsÚ	__class__s   &,€Úz/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/hyperclovax/configuration_hyperclovax.pyr   ÚHyperCLOVAXConfig.__post_init__n   su   ø€ ð �=‰=Ò Ø ×,Ñ,°×0HÑ0HÕHˆDŒMØ×#Ñ#Ò+Ø'+×'?Ñ'?ˆDÔ$ä‰ÒÑ' Ò'ð ×$Ñ$Ò,Ø(,¯©°tÕ(;ˆDÖ%ñ -ó    c                ó–   € V P                   V P                  ,          ^ 8w  d'   \        RV P                    RV P                   R24      hR# )zCValidates that `hidden_size` is divisible by `num_attention_heads`.zThe hidden size (z6) is not a multiple of the number of attention heads (z).N)r   r   Ú
ValueError)r   s   &r"   Úvalidate_architectureÚ'HyperCLOVAXConfig.validate_architecture}   sS   € à×Ñ˜d×6Ñ6Õ6¸!Ô;ÜØ# D×$4Ñ$4Ð#5ð 6Ø×2Ñ2Ð3°2ð7óð ñ <r$   c                ó  <€ V ^8„  d   Qh/ 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,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[;R&   S[S[,          R,          ;R&   S[;R&   S[S[ ,          ;R&   S[;R&   S[S[ ,          ;R&   S[S[ ,          ;R&   S[S[ ,          ;R&   S[R,          ;R&   S[ R,          ;R&   S[;R&   # )é   Ú
vocab_sizer   Úintermediate_sizeÚnum_hidden_layersr   Nr   Ú
hidden_actÚmax_position_embeddingsÚinitializer_rangeÚrms_norm_epsÚ	use_cacheÚpad_token_idÚbos_token_idÚeos_token_idÚtie_word_embeddingsÚrope_parametersÚattention_biasÚattention_dropoutÚmlp_biasÚembedding_multiplierÚlogits_scalingÚresidual_multiplierr   r   Úuse_post_norm)ÚintÚstrÚfloatÚboolÚlistr   Údict)ÚformatÚ__classdict__s   "€r"   Ú__annotate__ÚHyperCLOVAXConfig.__annotate__   s·  ø‡ ‚ ñh Ññi ñj Ññk ñl Ñ"ñm ñn Ñño ñp Ñ!ñq ñr ˜t�Ñ*ñs ñt Ññu ñv !Ñ'ñw ñx Ñ#ñy ñz Ññ{ ñ| Ññ} ñ~ ˜•*Ñ#ñ ñ@ ˜•*Ñ ñA ñB ™™S�	•/ DÕ(Ñ,ñC ñD Ñ%ñE ñF $¡dÕ*¨TÕ1Ñ8ñG ñH Ñ ñI ñJ ™s•{Ñ(ñK ñL ÑñM ñN  ¡#�+Ñ+ñO ñP ™C•KÑ%ñQ ñR ¡�Ñ*ñS ñX   $�,Ñ-ñY ñ\ �D�jÑñ] ñb Ñòc r$   )r   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/   r0   r1   r2   r3   r4   r5   r6   r7   r8   r9   r:   r;   r<   r=   r   r   r>   r   r'   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r!   rF   s   @@r"   r	   r	      s#  ù‡ € ñð> €JØ#4Ð"5Ðð 	$ YØ# YØ# YØ# YØ  )Ø 	Ø  )ðÐð 	˜+˜¨Ð(9Ð:Ø�OÐ%5Ð6¸Ð8IÐJØ�/Ð" _Ð$5Ð6ðÐð €JØ€KØ"ÐØÐØ!ÐØ&*ÐØ€JØ#'ÐØ#ÐØ€LØ€IØ#€LØ €LØ+,€LØ %ÐØ48€OØ €NØ%(ÐØ€HØ(+ÐØ"%€NØ'*Ðð *.Ðà€Hð €Mõ<ò÷E … r$   r	   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r	   Ú__all__r   r$   r"   Ú<module>r[      sL   ðõ( /å 3Ý 1Ý #ñ ÐIÔJØôfÐ(ó fó ó KðfðR Ð
‚r$   