
    Z jT                     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)auto_docstring   )PreTrainedConfig)RopeParameterszarcee-ai/AFM-4.5B)
checkpointc                     ^  \ rS rSr% SrSrS/r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'   Sr\\S'   Sr\
\S'   Sr\\S'   Sr\\S'   S r\\S!'   Sr\
S-  \S"'   S#r\
S-  \S$'   S%r\
\\
   -  S-  \S&'   S'r\\S('   Sr\\ -  S-  \S)'   S'r!\\S*'   S+r"\\
-  \S,'   S'r#\\S-'   Sr$\
S-  \S.'   U 4S/ jr%S0 r&S1r'U =r($ )2ArceeConfig   a[  
```python
>>> from transformers import ArceeModel, ArceeConfig

>>> # Initializing an Arcee AFM-4.5B-Base style configuration
>>> configuration = ArceeConfig()

>>> # Initializing a model from the AFM-4.5B-Base style configuration
>>> model = ArceeModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```arcee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.up_projzlayers.*.mlp.down_proj	input_idsinputs_embedshidden_statesattention_mask)embed_tokenslayersnormi }  
vocab_sizei 
  hidden_sizei H  intermediate_size    num_hidden_layersnum_attention_headsNnum_key_value_headsrelu2
hidden_acti   max_position_embeddingsg{Gz?initializer_rangegh㈵>rms_norm_epsT	use_cachepad_token_idi  bos_token_idi eos_token_idFtie_word_embeddingsrope_parametersattention_biasg        attention_dropoutmlp_biashead_dimc                    > U R                   c  U R                  U R                  -  U l         U R                  c  U R                  U l        [        TU ]  " S0 UD6  g )N )r,   r   r   r   super__post_init__)selfkwargs	__class__s     ~/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/arcee/configuration_arcee.pyr0   ArceeConfig.__post_init__S   sO    ==  ,,0H0HHDM##+'+'?'?D$''    c                     U R                   U R                  -  S:w  a&  [        SU R                    SU R                   S35      eg)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   
ValueError)r1   s    r4   validate_architecture!ArceeConfig.validate_architecture[   sS    d666!;#D$4$4#5 622327  <r6   )r,   r   ))__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr   int__annotations__r   r   r   r   r   r   strr    r!   floatr"   r#   boolr$   r%   r&   listr'   r(   r   dictr)   r*   r+   r,   r0   r9   __static_attributes____classcell__)r3   s   @r4   r
   r
      st    J#4"5%.%.%.%. )"+ &(9:#%568IJ!"_$56 JK"s"s!!&*t*J#'S'#u#L%It#L#*#%L#*%+1L#S	/D(1 %%48O^d*T18 ND %(us{(HdHcDj( r6   r
   N)
huggingface_hub.dataclassesr   transformers.utilsr   configuration_utilsr   modeling_rope_utilsr   r
   __all__r.   r6   r4   <module>rR      sJ   * / - 3 1 ./B" B  0BJ /r6   