§
    ‚ŠtjÔ  ã                   óŒ   — 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	d
S )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                 óŽ   •— | j         €#d„ t          | j        ¦  «        D ¦   «         | _          t          ¦   «         j        di |¤Ž d S )Nc                 ó@   — g | ]}t          |d z   dz  ¦  «        rdnd‘ŒS )r(   r*   Úsliding_attentionÚfull_attention)Úbool)Ú.0Úis     úu/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/vaultgemma/configuration_vaultgemma.pyú
<listcomp>z2VaultGemmaConfig.__post_init__.<locals>.<listcomp>^   sA   € ð  ð  ð  ØST¥t¨Q°©U°a©KÑ'8Ô'8ÐNÐ#Ð#Ð>Nð ð  ð  ó    © )r2   Úranger   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €r<   rB   zVaultGemmaConfig.__post_init__\   s^   ø€ ØÔÐ#ð ð  ÝX]Ð^bÔ^tÑXuÔXuð ñ  ô  ˆDÔð 	�‰ŒÔÐ'Ð' Ð'Ð'Ð'Ð'Ð'r>   c                 ól   — | j         | j        z  dk    r t          d| j         › d| j        › d�¦  «        ‚dS )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)rC   s    r<   Úvalidate_architecturez&VaultGemmaConfig.validate_architectured   s[   € àÔ˜dÔ6Ñ6¸!Ò;Ð;Ýð7 DÔ$4ð 7ð 7ØÔ2ð7ð 7ð 7ñô ð ð <Ð;r>   )+Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planr   ÚintÚ__annotations__r   r   r   r   r   r    r"   Ústrr#   r$   Úfloatr%   r&   r9   r'   r)   Úlistr+   r,   r-   r   Údictr.   r/   r0   r1   r2   r3   r4   rB   rH   Ú__classcell__)rE   s   @r<   r
   r
      s‹  ø€ € € € € € ðð ð$ €JØ#4Ð"5Ðà%.Ø%.Ø%.Ø%.Ø"+Ø )Ø"+ðð Ðð &˜¨Ð(9Ð:Ø#Ð%5Ð6¸Ð8IÐJØ!Ð" _Ð$5Ð6ðð Ðð €J�ÐÐÑØ€K�ÐÐÑØ!Ð�sÐ!Ð!Ñ!ØÐ�sÐÐÑØ Ð˜Ð Ð Ñ Ø Ð˜Ð Ð Ñ Ø€HˆcÐÐÑØ0Ð�sÐ0Ð0Ñ0Ø#'Ð˜SÐ'Ð'Ñ'Ø#Ð�uÐ#Ð#Ñ#Ø€L�%ÐÐÑØ€IˆtÐÐÑØ €L�#˜‘*Ð Ð Ñ Ø+,€L�#˜˜Sœ	‘/ DÑ(Ð,Ð,Ñ,Ø €L�#˜‘*Ð Ð Ñ Ø $Ð˜Ð$Ð$Ñ$Ø48€O�^ dÑ*¨TÑ1Ð8Ð8Ñ8Ø €N�DÐ Ð Ñ Ø,/Ð�s˜U‘{ TÑ)Ð/Ð/Ñ/Ø!$Ð˜3Ð$Ð$Ñ$Ø!%€N�C˜$‘JÐ%Ð%Ñ%Ø$(€K��c”˜TÑ!Ð(Ð(Ñ(Ø,0Ð˜U T™\Ð0Ð0Ñ0Ø+/Ð˜E D™LÐ/Ð/Ñ/ð(ð (ð (ð (ð (ðð ð ð ð ð ð r>   r
   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r?   r>   r<   ú<module>r]      s¶   ðð, /Ð .Ð .Ð .Ð .Ð .à 3Ð 3Ð 3Ð 3Ð 3Ð 3Ø 1Ð 1Ð 1Ð 1Ð 1Ð 1Ø #Ð #Ð #Ð #Ð #Ð #ð €Ð1Ð2Ñ2Ô2ØðKð Kð Kð Kð KÐ'ñ Kô Kñ „ñ 3Ô2ðKð\ Ð
€€€r>   