Ë
    ÜÓ^jÔ  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google/vaultgemma-1b)Ú
checkpointc                   ó  ‡ — 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e
d#<   d$Ze	d%z  e
d&<   d'Ze	ee	   z  d%z  e
d(<   d)Ze	d%z  e
d*<   d"Zee
d+<   d%Zee z  d%z  e
d,<   d-Z!ee
d.<   d/Z"e	ez  d%z  e
d0<   dZ#e	e
d1<   d2Z$e	d%z  e
d3<   d%Z%ee   d%z  e
d4<   d5Z&ed%z  e
d6<   d7Z'ed%z  e
d8<   ˆ fd9„Z(d:„ Z)ˆ xZ*S );ÚVaultGemmaConfiga(  
    query_pre_attn_scalar (`float`, *optional*, defaults to 256):
        scaling factor used on the attention scores
    final_logit_softcapping (`float`, *optional*, defaults to 30.0):
        scaling factor when applying tanh softcapping on the logits.
    attn_logit_softcapping (`float`, *optional*, defaults to 50.0):
        scaling factor when applying tanh softcapping on the attention scores.

    ```python
    >>> from transformers import VaultGemmaModel, VaultGemmaConfig
    >>> # Initializing a VaultGemma vaultgemma-7b style configuration
    >>> configuration = VaultGemmaConfig()
    >>> # Initializing a model from the vaultgemma-7b style configuration
    >>> model = VaultGemmaModel(configuration)
    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```Ú
vaultgemmaÚ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 $  Úintermediate_sizeé   Únum_hidden_layersé   Únum_attention_headsé   Únum_key_value_headsé   Úhead_dimÚgelu_pytorch_tanhÚhidden_activationi    Úmax_position_embeddingsg{®Gáz”?Úinitializer_rangeg�íµ ÷Æ°>Úrms_norm_epsTÚ	use_cacher   NÚpad_token_idé   Úeos_token_idé   Úbos_token_idÚtie_word_embeddingsÚrope_parametersFÚattention_biasg        Úattention_dropoutÚquery_pre_attn_scalari   Úsliding_windowÚlayer_typesg      >@Úfinal_logit_softcappingg      I@Úattn_logit_softcappingc                 ó¼   •— | j                   €;t        | j                  «      D �cg c]  }t        |dz   dz  «      rdnd‘Œ c}| _         t	        ‰| �  di |¤Ž y c c}w )Nr(   r*   Úsliding_attentionÚfull_attention© )r2   Úranger   ÚboolÚsuperÚ__post_init__)ÚselfÚkwargsÚiÚ	__class__s      €ú‚/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/vaultgemma/configuration_vaultgemma.pyr<   zVaultGemmaConfig.__post_init__\   s`   ø€ Ø×ÑÐ#äX]Ð^b×^tÑ^tÓXuö ØST¤t¨Q°©U°a©KÔ'8Ñ#Ð>NÑNò ˆDÔô 	‰ÑÑ' Ó'ùò	 s   ¥A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)r=   s    rA   Úvalidate_architecturez&VaultGemmaConfig.validate_architectured   sS   € à×Ñ˜d×6Ñ6Ñ6¸!Ò;ÜØ# D×$4Ñ$4Ð#5ð 6Ø×2Ñ2Ð3°2ð7óð ð <ó    )+Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planr   ÚintÚ__annotations__r   r   r   r   r   r    r"   Ústrr#   r$   Úfloatr%   r&   r:   r'   r)   Úlistr+   r,   r-   r   Údictr.   r/   r0   r1   r2   r3   r4   r<   rD   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Ð�sÓØ Ð˜Ó Ø Ð˜Ó Ø€HˆcÓØ0Ð�sÓ0Ø#'Ð˜SÓ'Ø#Ð�uÓ#Ø€L�%ÓØ€IˆtÓØ €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø €L�#˜‘*Ó Ø $Ð˜Ó$Ø48€O�^ dÑ*¨TÑ1Ó8Ø €N�DÓ Ø,/Ð�s˜U‘{ TÑ)Ó/Ø!$Ð˜3Ó$Ø!%€N�C˜$‘JÓ%Ø$(€K��c‘˜TÑ!Ó(Ø,0Ð˜U T™\Ó0Ø+/Ð˜E D™LÓ/ô(örE   r
   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r8   rE   rA   ú<module>rZ      sK   ðõ, /å 3Ý 1Ý #ñ Ð1Ô2ØôKÐ'ó Kó ó 3ðKð\ Ð
�rE   