+
    œ°³je  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 configuration)Ústrict)ÚPreTrainedConfig)Úauto_docstringzopenai-community/openai-gpt)Ú
checkpointc                   ó˜   a € ] tR t^t o 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V 3R ltRtV tR# )ÚOpenAIGPTConfiga^	  
afn (`str` or `Callable`, *optional*, defaults to `"gelu"`):
    The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
    `"relu"`, `"silu"` and `"gelu_new"` are supported.
layer_norm_epsilon (`float`, *optional*, defaults to 1e-05):
    The epsilon to use in the layer normalization layers
summary_type (`str`, *optional*, defaults to `"cls_index"`):
    Argument used when doing sequence summary, used in the models [`OpenAIGPTDoubleHeadsModel`] and
    [`OpenAIGPTDoubleHeadsModel`].
    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 [`OpenAIGPTDoubleHeadsModel`] and
    [`OpenAIGPTDoubleHeadsModel`].
    Whether or not to add a projection after the vector extraction.
summary_activation (`str`, *optional*):
    Argument used when doing sequence summary, used in the models [`OpenAIGPTDoubleHeadsModel`] and
    [`OpenAIGPTDoubleHeadsModel`].
    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 [`OpenAIGPTDoubleHeadsModel`] and
    [`OpenAIGPTDoubleHeadsModel`].
    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 [`OpenAIGPTDoubleHeadsModel`] and
    [`OpenAIGPTDoubleHeadsModel`].
    The dropout ratio to be used after the projection and activation.

Examples:

```python
>>> from transformers import OpenAIGPTConfig, OpenAIGPTModel

>>> # Initializing a GPT configuration
>>> configuration = OpenAIGPTConfig()

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

>>> # Accessing the model configuration
>>> configuration = model.config
```z
openai-gptÚmax_position_embeddingsÚn_positionsÚhidden_sizeÚn_embdÚnum_attention_headsÚn_headÚnum_hidden_layersÚn_layeriž  i   i   Úgelugš™™™™™¹?gñhãˆµøä>g{®Gáz”?Ú	cls_indexTNc                ó¢  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;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,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[;R&   # )é   Ú
vocab_sizer	   r   r   r   ÚafnÚresid_pdropÚ
embd_pdropÚ
attn_pdropÚlayer_norm_epsilonÚinitializer_rangeÚsummary_typeÚsummary_use_projNÚsummary_activationÚsummary_proj_to_labelsÚsummary_first_dropoutÚpad_token_idÚbos_token_idÚeos_token_idÚtie_word_embeddings)ÚintÚstrÚfloatÚboolÚlist)ÚformatÚ__classdict__s   "€Úp/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/openai/configuration_openai.pyÚ__annotate__ÚOpenAIGPTConfig.__annotate__   sZ  ø‡ ‚ ñt Ññu ñv Ññw ñx Ññy ñz Ññ{ ñ| Ññ} ñ~ 
Ññ ñ@ ™•Ñ"ñA ñB ™•Ñ!ñC ñD ™•Ñ!ñE ñF Ñ$ñG ñH Ñ#ñI ñJ Ñ#ñK ñL Ñ!ñM ñN ˜d�
Ñ)ñO ñP !Ñ'ñQ ñR !¡3�;Ñ,ñS ñT ˜•*Ñ#ñU ñV ˜•*Ñ#ñW ñX ™™S�	•/ DÕ(Ñ/ñY ñZ Ñ$ò[ ó    © )Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚattribute_mapr   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__)r*   s   @r+   r   r      s¢   ø‡ € ñ-ð^ €Jà! =Ø�xØ˜xØ˜Yð	€Mð €JØ€KØ€FØ€GØ€FØ€CØ"€KØ!€JØ!€JØ $ÐØ#ÐØ#€LØ!ÐØ%)ÐØ#'ÐØ),ÐØ#€LØ#€LØ+/€LØ $Ð÷[ ƒ r.   r   N)	r4   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r   Ú__all__r/   r.   r+   Ú<module>r>      sK   ðñ å .å 3Ý #ñ Ð8Ô9ØôK%Ð&ó K%ó ó :ðK%ð\ Ð
‚r.   