
    Z j8                     |    S r SSKJr  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)zLLaMA model configuration    )strict   )PreTrainedConfig)RopeParameters)auto_docstring)intervalzmeta-llama/Llama-2-7b-hf)
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'   Sr\\S'   Sr\
\S'   \" SSS9" SS 9r\\S!'   S"r\\S#'   S$r\\S%'   Sr\
S-  \S&'   S'r\
S-  \S('   S)r\
\\
   -  S-  \S*'   S'r\
S-  \S+'   S,r\\S-'   Sr \!\"-  S-  \S.'   S,r#\\S/'   Sr$\
\-  S-  \S0'   S,r%\\S1'   Sr&\
S-  \S2'   U 4S3 jr'S4 r(S5r)U =r*$ )6LlamaConfig   aP  
```python
>>> from transformers import LlamaModel, LlamaConfig

>>> # Initializing a LLaMA llama-7b style configuration
>>> configuration = LlamaConfig()

>>> # Initializing a model from the llama-7b style configuration
>>> model = LlamaModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```llama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_headsNnum_key_value_headssilu
hidden_acti   max_position_embeddingsg        g      ?)minmaxg{Gz?)defaultinitializer_rangegư>rms_norm_epsT	use_cachepad_token_id   bos_token_id   eos_token_idpretraining_tpFtie_word_embeddingsrope_parametersattention_bias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 )r3   r   r   r   super__post_init__)selfkwargs	__class__s     ~/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/llama/configuration_llama.pyr7   LlamaConfig.__post_init__V   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)r8   s    r;   validate_architecture!LlamaConfig.validate_architecture^   sS    d666!;#D$4$4#5 622327  <r=   )r3   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   r%   floatr&   r'   boolr(   r*   r,   listr-   r.   r/   r   dictr0   r1   r2   r3   r7   r@   __static_attributes____classcell__)r:   s   @r;   r   r      s    J#4"5 &/%.%.%."+ )"+ &(9:#%568IJ!"_$56 JK"s"s!!&*t*J#'S''CS9$GuGL%It#L#*# L#* +,L#S	/D(,!"NC$J" %%48O^d*T18 ND ,/sU{T)/HdHcDj( r=   r   N)rF   huggingface_hub.dataclassesr   configuration_utilsr   modeling_rope_utilsr   utilsr   utils.type_validatorsr   r   __all__r5   r=   r;   <module>rZ      sP   &   . 3 1 # - 56E" E  7EP /r=   