+
    œ°³jÈ  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OpenAI GPT-2 configuration)Ústrict)ÚPreTrainedConfig)Úauto_docstringzopenai-community/gpt2)Ú
checkpointc                   ó¶   a € ] tR t^t o RtRtR.tRRRRRR	R
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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 t$R# )Ú
GPT2Configa¸  
summary_type (`string`, *optional*, defaults to `"cls_index"`):
    Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`].
    Has to be one of the following options:
        - `"last"`: Take the last token hidden state (like XLNet).
        - `"first"`: Take the first token hidden state (like BERT).
        - `"mean"`: Take the mean of all tokens hidden states.
        - `"cls_index"`: Supply a Tensor of classification token position (like GPT/GPT-2).
        - `"attn"`: Not implemented now, use multi-head attention.
summary_use_proj (`bool`, *optional*, defaults to `True`):
    Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`].
    Whether or not to add a projection after the vector extraction.
summary_activation (`str`, *optional*):
    Argument used when doing sequence summary. Used in for the multiple choice head in
    [`GPT2DoubleHeadsModel`].
    Pass `"tanh"` for a tanh activation to the output, any other value will result in no activation.
summary_proj_to_labels (`bool`, *optional*, defaults to `True`):
    Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`].
    Whether the projection outputs should have `config.num_labels` or `config.hidden_size` classes.
summary_first_dropout (`float`, *optional*, defaults to 0.1):
    Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`].
    The dropout ratio to be used after the projection and activation.
scale_attn_by_inverse_layer_idx (`bool`, *optional*, defaults to `False`):
    Whether to additionally scale attention weights by `1 / layer_idx + 1`.
reorder_and_upcast_attn (`bool`, *optional*, defaults to `False`):
    Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention
    dot-product/softmax to float() when training with mixed precision.

Example:

```python
>>> from transformers import GPT2Config, GPT2Model

>>> # Initializing a GPT2 configuration
>>> configuration = GPT2Config()

>>> # Initializing a model (with random weights) from the configuration
>>> model = GPT2Model(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```Úgpt2Úpast_key_valuesÚhidden_sizeÚn_embdÚmax_position_embeddingsÚn_positionsÚnum_attention_headsÚn_headÚnum_hidden_layersÚn_layeriQÄ  i   i   NÚgelu_newgš™™™™™¹?gñhãˆµøä>g{®Gáz”?Ú	cls_indexTiPÄ  Fc                óø  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R&   S[;R&   S[S[ ,          ;R	&   S[S[ ,          ;R
&   S[S[ ,          ;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[R,          ;R&   S[;R&   S[S[ ,          ;R&   S[;R&   S[;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[ R,          ;R&   S[;R&   S[;R&   S[;R&   S[;R&   # )é   Ú
vocab_sizer   r   r   r   NÚn_innerÚactivation_functionÚresid_pdropÚ
embd_pdropÚ
attn_pdropÚlayer_norm_epsilonÚinitializer_rangeÚsummary_typeÚsummary_use_projÚsummary_activationÚsummary_proj_to_labelsÚsummary_first_dropoutÚscale_attn_weightsÚ	use_cacheÚbos_token_idÚeos_token_idÚpad_token_idÚscale_attn_by_inverse_layer_idxÚreorder_and_upcast_attnÚadd_cross_attentionÚtie_word_embeddings)ÚintÚstrÚfloatÚboolÚlist)ÚformatÚ__classdict__s   "€Úl/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/gpt2/configuration_gpt2.pyÚ__annotate__ÚGPT2Config.__annotate__   s¸  ø‡ ‚ ñn Ñño ñp Ññq ñr Ññs ñt Ññu ñv Ññw ñx �4�ZÑñy ñz Ñ)ñ{ ñ| ™•Ñ"ñ} ñ~ ™•Ñ!ñ ñ@ ™•Ñ!ñA ñB Ñ$ñC ñD Ñ#ñE ñF Ñ#ñG ñH Ñ!ñI ñJ ˜d�
Ñ)ñK ñL !Ñ'ñM ñN !¡3�;Ñ,ñO ñP Ñ#ñQ ñR ÑñS ñT ˜•*Ñ$ñU ñV ™™S�	•/ DÕ(Ñ0ñW ñX ˜•*Ñ#ñY ñZ &*Ñ1ñ[ ñ\ "Ñ)ñ] ñ^ Ñ%ñ_ ñ` Ñ$òa ó    © )%Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚattribute_mapr   r   r   r   r   r   r   r   r   r   r   r   r   r   r    r!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__)r2   s   @r3   r   r      sÎ   ø‡ € ñ)ðV €JØ#4Ð"5Ðà�xØ! =Ø˜xØ˜Yð	€Mð €JØ€KØ€FØ€GØ€FØ€GØ)ÐØ"€KØ!€JØ!€JØ $ÐØ#ÐØ#€LØ!ÐØ%)ÐØ#'ÐØ),ÐØ#ÐØ€IØ$€LØ+0€LØ#€LØ,1Ð#Ø$)ÐØ %ÐØ $Ð÷a ƒ r6   r   N)	r<   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r   Ú__all__r7   r6   r3   Ú<module>rG      sJ   ðñ !å .å 3Ý #ñ Ð2Ô3ØôN%Ð!ó N%ó ó 4ðN%ðb ˆ.‚r6   