
    iI                     r    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
)    )strict   )PreTrainedConfig)RopeParameters)auto_docstringzgoogle/gemma-7b)
checkpointc                      e Zd ZU dZdZdgZddddddddZdgdgfd	d
gd	gfd	gd	gfd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$z  e
d+<   d,Z!ee
d-<   d.Z"ee	z  e
d/<   d$Z#ed$z  e
d0<   y$)1GemmaConfiga  
    use_bidirectional_attention (`bool`, *optional*):
        If True, the model will attend to all text tokens instead of using a causal mask.

    ```python
    >>> from transformers import GemmaModel, GemmaConfig
    >>> # Initializing a Gemma gemma-7b style configuration
    >>> configuration = GemmaConfig()
    >>> # Initializing a model from the gemma-7b style configuration
    >>> model = GemmaModel(configuration)
    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```gemmapast_key_valuescolwise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_proj	input_idsinputs_embedshidden_statesattention_mask)embed_tokenslayersnormi  
vocab_sizei   hidden_sizei `  intermediate_size   num_hidden_layers   num_attention_headsnum_key_value_heads   head_dimgelu_pytorch_tanh
hidden_acti    max_position_embeddingsg{Gz?initializer_rangegư>rms_norm_epsT	use_cacher   Npad_token_id   eos_token_id   bos_token_idtie_word_embeddingsrope_parametersFattention_biasg        attention_dropoutuse_bidirectional_attention)$__name__
__module____qualname____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr   int__annotations__r   r   r   r   r   r   r!   strr"   r#   floatr$   r%   boolr&   r(   listr*   r+   r,   r   dictr-   r.   r/        ~/var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/transformers/models/gemma/configuration_gemma.pyr
   r
      sd    J#4"5%.%.%.%."+ )"+ &(9:#%568IJ!"_$56 JK"s"s!!!!Hc)J)#'S'#u#L%It L#* +,L#S	/D(, L#*  $$48O^d*T18 ND %(us{(/33r@   r
   N)
huggingface_hub.dataclassesr   configuration_utilsr   modeling_rope_utilsr   utilsr   r
   __all__r?   r@   rA   <module>rG      sG   . / 3 1 # ,-34" 34  .34l /r@   