Ë
    ÛÓ^jý  ã                   ór   — 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
)é    )Ústricté   )ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzCohereForAI/c4ai-command-r-v01)Ú
checkpointc                   óÖ  ‡ — e Zd ZU dZdZdg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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e
d <   d!Zee
d"<   d#Ze	dz  e
d$<   d%Ze	dz  e
d&<   d'Ze	ee	   z  dz  e
d(<   d!Zee
d)<   dZee z  dz  e
d*<   d+Z!ee
d,<   d-Z"ee	z  e
d.<   d/Z#e	dz  e
d0<   dZ$ee   dz  e
d1<   ˆ fd2„Z%ˆ xZ&S )3ÚCohere2Configa  
    logit_scale (`float`, *optional*, defaults to 0.0625):
        The scaling factor for the output logits.

    ```python
    >>> from transformers import Cohere2Model, Cohere2Config

    >>> # Initializing a Cohere Nextmodel configuration
    >>> configuration = Cohere2Config()

    >>> # Initializing a model from the Cohere2 configuration
    >>> model = Cohere2Model(configuration) # doctest: +SKIP

    >>> # Accessing the model configuration
    >>> configuration = model.config # doctest: +SKIP
    ```
    Úcohere2Úpast_key_valuesÚ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      °?Úlogit_scaleé(   Únum_hidden_layersé@   Únum_attention_headsNÚ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_dropouti   Úsliding_windowÚlayer_typesc                 óV  •— | j                   €| j                  | _         | j                  | j                  z  | _        | j                  €M|j                  dd«      }t        | j                  «      D �cg c]  }t        |dz   |z  «      rdnd‘Œ c}| _        t        ‰| �(  di |¤Ž y c c}w )NÚsliding_window_patterné   é   Úsliding_attentionÚfull_attention© )r   r   r   Úhead_dimr.   ÚpopÚranger   ÚboolÚsuperÚ__post_init__)ÚselfÚkwargsÚ_sliding_window_patternÚiÚ	__class__s       €ú|/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/cohere2/configuration_cohere2.pyr;   zCohere2Config.__post_init__X   s®   ø€ Ø×#Ñ#Ð+Ø'+×'?Ñ'?ˆDÔ$ð ×(Ñ(¨D×,DÑ,DÑDˆŒð ×ÑÐ#à&,§j¡jÐ1IÈ1Ó&MÐ#ô ˜t×5Ñ5Ó6ö àô (,¨Q°©UÐ6MÑ,MÔ'NÑ#ÐTdÑdò ˆDÔô
 	‰ÑÑ' Ó'ùò s   Á2B&)'Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planr   ÚintÚ__annotations__r   r   r   Úfloatr   r   r   r    Ústrr!   r"   r#   r$   r9   r%   r'   r(   Úlistr)   r*   r   Údictr+   r,   r-   r.   r;   Ú__classcell__)r@   s   @rA   r
   r
      s…  ø… ñð$ €JØ#4Ð"5Ðà%.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�EÓ 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‘{Ó(Ø!%€N�C˜$‘JÓ%Ø$(€K��c‘˜TÑ!Ó(÷(ð (ó    r
   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r5   rQ   rA   ú<module>rW      sK   ðõ* /å 3Ý 1Ý #ñ Ð;Ô<ØôJ(Ð$ó J(ó ó =ðJ(ðZ Ð
�rQ   