+
    œ°³j¾  ã                   ól   € R 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OPT model configuration)Ústrict)ÚPreTrainedConfig)Úauto_docstringzfacebook/opt-350m)Ú
checkpointc                   ó    a a€ ] tR t^t oRtRtR.tRtRt^t	Rt
RtRtR	tR
tRtRt^tRtRtRtRt^t^t^tRtRtRtV 3R ltV3R ltRtVtV ;t # )Ú	OPTConfigaÂ  
do_layer_norm_before (`bool`, *optional*, defaults to `True`):
    Whether to perform layer normalization before the attention block.
word_embed_proj_dim (`int`, *optional*):
    `word_embed_proj_dim` can be set to down-project word embeddings, *e.g.* `opt-350m`. Defaults to
    `hidden_size`.
enable_bias (`bool`, *optional*, defaults to `True`):
    Whether or not if the linear layers in the attention blocks should use the bias term.
layer_norm_elementwise_affine (`bool`, *optional*, defaults to `True`):
    Whether or not if the layer norms should have learnable parameters.

Example:

```python
>>> from transformers import OPTConfig, OPTModel

>>> # Initializing a OPT facebook/opt-large style configuration
>>> configuration = OPTConfig()

>>> # Initializing a model (with random weights) from the facebook/opt-large style configuration
>>> model = OPTModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```ÚoptÚpast_key_valuesi`Ä  i   i   i   TFNgš™™™™™¹?g        Úrelug{®Gáz”?c                ó~   <€ V P                   e   V P                   MV P                  V n         \        SV `  ! R/ VB  R # )N© )Úword_embed_proj_dimÚhidden_sizeÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s   &,€Új/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/opt/configuration_opt.pyr   ÚOPTConfig.__post_init__L   s:   ø€ à(,×(@Ñ(@Ò(LˆD×$Ò$ÐRV×RbÑRbð 	Ô ô 	‰ÒÑ' Ô'ó    c                óž  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[;R&   S[;R&   S[ R,          ;R	&   S[S[ ,          ;R
&   S[S[ ,          ;R&   S[ ;R&   S[;R&   S[S[ ,          ;R&   S[;R&   S[;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[;R&   S[;R&   S[;R&   # )é   Ú
vocab_sizer   Únum_hidden_layersÚffn_dimÚmax_position_embeddingsÚdo_layer_norm_beforeÚ_remove_final_layer_normNr   ÚdropoutÚattention_dropoutÚnum_attention_headsÚactivation_functionÚ	layerdropÚinit_stdÚ	use_cacheÚpad_token_idÚbos_token_idÚeos_token_idÚenable_biasÚlayer_norm_elementwise_affineÚtie_word_embeddings)ÚintÚboolÚfloatÚstrÚlist)ÚformatÚ__classdict__s   "€r   Ú__annotate__ÚOPTConfig.__annotate__   se  ø‡ ‚ ñ@ ÑñA ñB ÑñC ñD ÑñE ñF ÑñG ñH !Ñ'ñI ñJ Ñ%ñK ñL #Ñ*ñM ñN ˜t�Ñ*ñO ñP ‘S�[ÑñQ ñR ™s•{Ñ(ñS ñT Ñ!ñU ñV Ñ%ñW ñX ‘s�{Ñ ñY ñZ Ññ[ ñ\ Ññ] ñ^ ˜•*Ñ ñ_ ñ` ˜•*Ñ ña ñb ™™S�	•/ DÕ(Ñ,ñc ñd Ññe ñf $(Ñ.ñg ñh Ñ$òi r   )r   )!Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferencer   r   r   r   r   r   r   r   r   r    r!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   r   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r   r2   s   @@r   r   r      sš   ù‡ € ñð4 €JØ#4Ð"5Ðà€JØ€KØÐØ€GØ#'ÐØ!%ÐØ%*ÐØ&*ÐØ€GØ%(ÐØ!ÐØ%ÐØ €IØ€HØ€IØ €LØ €LØ+,€LØ€KØ*.Ð!Ø $Ðõ(÷m … r   r   N)	r9   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r   Ú__all__r   r   r   Ú<module>rD      sG   ðñ å .å 3Ý #ñ Ð.Ô/Øô8(Ð ó 8(ó ó 0ð8(ðv ˆ-‚r   