Ë
    ÛÓ^j>  ã                   óf   — 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auto_docstringzfacebook/cwm)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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$Ze	e
d%<   d"Ze	ee	   z  d"z  e
d&<   d'Ze	e
d(<   d)Zee
d*<   d"Zed"z  e
d+<   d,Z ee	z  e
d-<   d)Z!ee
d.<   d/Z"e	e
d0<   d1Z#d2Z$e	e
d3<   d"Z%ee   d"z  e
d4<   ˆ fd5„Z&d6„ Z'ˆ xZ(S )7Ú	CwmConfigaf  
    ```python
    >>> from transformers import CwmModel, CwmConfig

    >>> # Initializing a Cwm cwm-7b style configuration
    >>> configuration = CwmConfig()

    >>> # Initializing a model from the cwm-7b style configuration
    >>> model = CwmModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```ÚcwmÚ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 õ Ú
vocab_sizei   Úhidden_sizei T  Úintermediate_sizeé@   Únum_hidden_layersé0   Únum_attention_headsé   Únum_key_value_headsÚsiluÚ
hidden_acti   Úmax_position_embeddingsg{®Gáz”?Úinitializer_rangegñhãˆµøä>Úrms_norm_epsTÚ	use_cacheNÚpad_token_idi ô Úbos_token_idÚeos_token_idé   Úpretraining_tpFÚtie_word_embeddingsÚrope_parametersg        Úattention_dropoutÚmlp_biasé€   Úhead_dimç    €„.Aé    Úsliding_windowÚlayer_typesc                 ó6  •— | j                   €dddddddœ| _         | j                  €4d}t        | j                  «      D �cg c]  }||z  d	k(  rd
nd‘Œ c}| _        | j                  rt        | j                  «      nd | _        t        | j                  «      | _        | j                  �| j                  ng d¢| _        | j                  €| j                  | j                  z  | _        | j                  €| j                  | _        t        ‰| �4  di |¤Ž y c c}w )Nr/   g      0@g      @g      ð?r0   Úllama3)Ú
rope_thetaÚfactorÚhigh_freq_factorÚlow_freq_factorÚ original_max_position_embeddingsÚ	rope_typeé   r   Úfull_attentionÚsliding_attention)iô iô i	ô © )r*   r2   Úranger   r1   ÚintÚlistr&   r.   r   r   r   ÚsuperÚ__post_init__)ÚselfÚkwargsÚwindow_patternÚiÚ	__class__s       €út/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/cwm/configuration_cwm.pyrC   zCwmConfig.__post_init__W   s  ø€ Ø×ÑÐ'à)ØØ$'Ø#&Ø48Ø%ñ$ˆDÔ ð ×ÑÐ#àˆNô ˜t×5Ñ5Ó6ö àð '(¨.Ñ&8¸AÒ&=Ñ!ÐDWÑWò ˆDÔð
 ;?×:MÒ:Mœc $×"5Ñ"5Ô6ÐSWˆÔÜ × 0Ñ 0Ó1ˆÔØ15×1BÑ1BÐ1N˜D×-Ò-ÒTlˆÔØ�=‰=Ð Ø ×,Ñ,°×0HÑ0HÑHˆDŒMØ×#Ñ#Ð+Ø'+×'?Ñ'?ˆDÔ$ä‰ÑÑ' Ó'ùò s   ÁDc                 óˆ   — | j                   | j                  z  dk7  r&t        d| j                   › d| j                  › d�«      ‚y)zOPart of `@strict`-powered validation. Validates the architecture of the config.r   zThe hidden size (z6) is not a multiple of the number of attention heads (z).N)r   r   Ú
ValueError)rD   s    rI   Úvalidate_architecturezCwmConfig.validate_architecturet   sS   € à×Ñ˜d×6Ñ6Ñ6¸!Ò;ÜØ# D×$4Ñ$4Ð#5ð 6Ø×2Ñ2Ð3°2ð7óð ð <ó    ))Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planr   r@   Ú__annotations__r   r   r   r   r   r   Ústrr    r!   Úfloatr"   r#   Úboolr$   r%   r&   rA   r(   r)   r*   Údictr+   r,   r.   Údefault_thetar1   r2   rC   rL   Ú__classcell__)rH   s   @rI   r	   r	      s„  ø… ñð €JØ#4Ð"5Ðð &/Ø%.Ø%.Ø%.Ø"+Ø )Ø"+ñÐð &˜¨Ð(9Ð:Ø#Ð%5Ð6¸Ð8IÐJØ!Ð" _Ð$5Ð6ñÐð €J�ÓØ€K�ÓØ"Ð�sÓ"ØÐ�sÓØ!Ð˜Ó!Ø Ð˜Ó Ø€J�ÓØ#)Ð˜SÓ)Ø#Ð�uÓ#Ø€L�%ÓØ€IˆtÓØ#€L�#˜‘*Ó#Ø€L�#ÓØ+/€L�#˜˜S™	‘/ DÑ(Ó/Ø€N�CÓØ %Ð˜Ó%Ø#'€O�T˜D‘[Ó'Ø%(Ð�u˜s‘{Ó(Ø€HˆdÓØ€HˆcÓØ€MØ€N�CÓØ$(€K��c‘˜TÑ!Ó(ô(ö:rM   r	   N)Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r	   Ú__all__r>   rM   rI   ú<module>ra      sF   ðõ, /å 3Ý #ñ ˜>Ô*Øô\Ð ó \ó ó +ð\ð~ ˆ-�rM   