Ë
    ÛÓ^j=  ã                   óv   — d Z ddlmZ ddlmZ ddlmZ ddlmZ  ed¬«      e G d	„ d
e«      «       «       Z	d
gZ
y)zCohere model configurationé    )Ústricté   )ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzCohereForAI/c4ai-command-r-v01)Ú
checkpointc                   óÒ  ‡ — e Zd ZU dZdZdgZdZddddddddœZdgd	gfd
dgd
gfd
gd
gfdœZdZ	e
ed<   dZe
ed<   dZe
ed<   dZedz  ed<   dZe
ed<   dZe
ed<   dZe
dz  ed<   dZeed<   dZe
ed<   dZeed<   d Zedz  ed!<   d"Zeed#<   d$Ze
dz  ed%<   d&Ze
dz  ed'<   d(Ze
ee
   z  dz  ed)<   d"Zeed*<   dZe e!z  dz  ed+<   d,Z"eed-<   d.Z#ee
z  dz  ed/<   d,Z$edz  ed0<   ˆ fd1„Z%ˆ xZ&S )2ÚCohereConfigaý  
    logit_scale (`float`, *optional*, defaults to 0.0625):
        The scaling factor for the output logits.

    ```python
    >>> from transformers import CohereModel, CohereConfig

    >>> # Initializing a Cohere model configuration
    >>> configuration = CohereConfig()

    >>> # Initializing a model from the Cohere configuration
    >>> model = CohereModel(configuration) # doctest: +SKIP

    >>> # Accessing the model configuration
    >>> configuration = model.config # doctest: +SKIP
    ```
    ÚcohereÚpast_key_valuesg    €„AÚcolwiseÚrowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projÚ	input_idsÚinputs_embedsÚhidden_statesÚattention_mask)Úembed_tokensÚlayersÚnormi è Ú
vocab_sizei    Úhidden_sizei X  Úintermediate_sizeg      °?NÚlogit_scaleé(   Únum_hidden_layersé@   Únum_attention_headsÚnum_key_value_headsÚsiluÚ
hidden_actÚmax_position_embeddingsg{®Gáz”?Úinitializer_rangegñhãˆµøä>Úlayer_norm_epsTÚ	use_cacher   Úpad_token_idé   Úbos_token_idiä Úeos_token_idÚtie_word_embeddingsÚrope_parametersFÚattention_biasg        Úattention_dropoutÚuse_qk_normc                 ó^   •— | j                   €| j                  | _         t        ‰| �  di |¤Ž y )N© )r   r   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €úz/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/cohere/configuration_cohere.pyr1   zCohereConfig.__post_init__W   s-   ø€ Ø×#Ñ#Ð+Ø'+×'?Ñ'?ˆDÔ$ä‰ÑÑ' Ó'ó    )'Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚdefault_thetaÚbase_model_tp_planÚbase_model_pp_planr   ÚintÚ__annotations__r   r   r   Úfloatr   r   r   r    Ústrr!   r"   r#   r$   Úboolr%   r'   r(   Úlistr)   r*   r   Údictr+   r,   r-   r1   Ú__classcell__)r4   s   @r5   r
   r
      s„  ø… ñð$ €JØ#4Ð"5ÐØ€Mà%.Ø%.Ø%.Ø%.Ø"+Ø )Ø"+ñÐð &˜¨Ð(9Ð:Ø#Ð%5Ð6¸Ð8IÐJØ!Ð" _Ð$5Ð6ñÐð
 €J�ÓØ€K�ÓØ"Ð�sÓ"Ø &€K�˜‘Ó&ØÐ�sÓØ!Ð˜Ó!Ø&*Ð˜˜t™Ó*Ø€J�ÓØ#'Ð˜SÓ'Ø#Ð�uÓ#Ø#'€N�E˜D‘LÓ'Ø€IˆtÓØ €L�#˜‘*Ó Ø €L�#˜‘*Ó Ø+1€L�#˜˜S™	‘/ DÑ(Ó1Ø $Ð˜Ó$Ø48€O�^ dÑ*¨TÑ1Ó8Ø €N�DÓ Ø,/Ð�u˜s‘{ TÑ)Ó/Ø$€K�˜‘Ó$÷(ð (r6   r
   N)r:   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r/   r6   r5   ú<module>rM      sK   ðñ& !å .å 3Ý 1Ý #ñ Ð;Ô<Øô=(Ð#ó =(ó ó =ð=(ð@ Ð
�r6   