+
    œ°³jò	  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StableLM model configuration)Ústrict)ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzstabilityai/stablelm-3b-4e1t)Ú
checkpointc                   ó    a a€ ] tR t^t o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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StableLmConfigaû  
use_parallel_residual (`bool`, *optional*, defaults to `False`):
    Whether to use a "parallel" formulation in each Transformer layer, which can provide a slight training
    speedup at large scales.
hidden_dropout (`float`, *optional*, defaults to 0.0):
    The dropout ratio after applying the MLP to the hidden states.

Example:

```python
>>> from transformers import StableLmModel, StableLmConfig

>>> # Initializing a StableLM stablelm-3b style configuration
>>> configuration = StableLmConfig()
```ÚstablelmÚpast_key_valuesi€Ä  i   i 
  Úsilui   g{®Gáz”?gñhãˆµøä>TFNg        c                óL   <€ VP                  R R4       \        SV `  ! R/ VB  R# )Úpartial_rotary_factorg      Ð?N© )Ú
setdefaultÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s   &,€Út/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/stablelm/configuration_stablelm.pyr   ÚStableLmConfig.__post_init__C   s$   ø€ Ø×ÑÐ1°4Ô8Ü‰ÒÑ' Ô'ó    c                óž  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[;R&   S[ ;R&   S[;R	&   S[;R
&   S[;R&   S[;R&   S[S[,          R,          ;R&   S[;R&   S[;R&   S[;R&   S[S[ ,          ;R&   S[S[ ,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[ R,          ;R&   # )é   Ú
vocab_sizeÚintermediate_sizeÚhidden_sizeÚnum_hidden_layersÚnum_attention_headsÚnum_key_value_headsÚ
hidden_actÚmax_position_embeddingsÚinitializer_rangeÚlayer_norm_epsÚ	use_cacheÚtie_word_embeddingsNÚrope_parametersÚuse_qkv_biasÚqk_layernormÚuse_parallel_residualÚhidden_dropoutÚattention_dropoutÚbos_token_idÚeos_token_idÚpad_token_id)ÚintÚstrÚfloatÚboolr   ÚdictÚlist)ÚformatÚ__classdict__s   "€r   Ú__annotate__ÚStableLmConfig.__annotate__   sS  ø‡ ‚ ñ, Ññ- ñ. Ñ!ñ/ ñ0 Ññ1 ñ2 Ññ3 ñ4 Ñ!ñ5 ñ6 Ñ!ñ7 ñ8 Ññ9 ñ: !Ñ'ñ; ñ< Ñ#ñ= ñ> Ñ"ñ? ñ@ ÑñA ñB Ñ%ñC ñD $¡dÕ*¨TÕ1Ñ8ñE ñF ÑñG ñH ÑñI ñJ  Ñ'ñK ñL ™C•KÑ%ñM ñN ™s•{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_inferencer   r   r   r   r   r   r    r!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   r,   r-   r.   r   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r   r6   s   @@r   r   r      s™   ù‡ € ñð  €JØ#4Ð"5Ðà€JØ!ÐØ€KØÐØ!ÐØ!ÐØ€JØ#'ÐØ#ÐØ"€NØ€IØ %ÐØ48€OØ€LØ€LØ"'ÐØ"%€NØ%(ÐØ €LØ+,€LØ#€Lõ(÷Y … r   r   N)r=   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r   Ú__all__r   r   r   Ú<module>rI      sK   ðñ #å .å 3Ý 1Ý #ñ Ð9Ô:Øô,(Ð%ó ,(ó ó ;ð,(ð^ Ð
‚r   