
    Z jI                     l    S SK Jr  SSKJr  SSKJr  SSKJr  \" SS9\ " S S	\5      5       5       rS	/r	g
)    )strict   )PreTrainedConfig)RopeParameters)auto_docstringzgoogle/gemma-7b)
checkpointc                      \ rS rSr% SrSrS/rSSSSSSSS.rS/S	/4S
S/S
/4S
/S
/4S.rSr	\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\\S'   Sr\
\S'   Sr\\S'   S r\\S!'   S"r\\S#'   S$r\
S%-  \S&'   S'r\
\\
   -  S%-  \S('   S)r\
S%-  \S*'   S"r\\S+'   S%r\ \!-  S%-  \S,'   S-r"\\S.'   S/r#\\
-  \S0'   S%r$\S%-  \S1'   S2r%g%)3GemmaConfig   a  
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____firstlineno____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/   r0   __static_attributes__r1       ~/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/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3rC   r
   N)
huggingface_hub.dataclassesr   configuration_utilsr   modeling_rope_utilsr   utilsr   r
   __all__r1   rC   rD   <module>rJ      sG   . / 3 1 # ,-34" 34  .34l /rC   