
    Z j=                     p    S 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Cohere model configuration    )strict   )PreTrainedConfig)RopeParameters)auto_docstringzCohereForAI/c4ai-command-r-v01)
checkpointc                     ^  \ rS 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'   Sr\\S'   Sr\\S'   Sr\S-  \S'   Sr\\S'   Sr\\S'   Sr\\S '   S!r\S-  \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-  \S0'   S-r%\S-  \S1'   U 4S2 jr&S3r'U =r($ )4CohereConfig   a  
logit_scale (`float`, *optional*, defaults to 0.0625):
    The scaling factor for the output logits.

```python
>>> from transformers import CohereModel, CohereConfig

>>> # Initializing a Cohere model configuration
>>> configuration = CohereConfig()

>>> # Initializing a model from the Cohere configuration
>>> model = CohereModel(configuration) # doctest: +SKIP

>>> # Accessing the model configuration
>>> configuration = model.config # doctest: +SKIP
```
coherepast_key_valuesg    A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 X  intermediate_sizeg      ?Nlogit_scale(   num_hidden_layers@   num_attention_headsnum_key_value_headssilu
hidden_actmax_position_embeddingsg{Gz?initializer_rangegh㈵>layer_norm_epsT	use_cacher   pad_token_id   bos_token_idi eos_token_idtie_word_embeddingsrope_parametersFattention_biasg        attention_dropoutuse_qk_normc                 b   > U R                   c  U R                  U l         [        TU ]  " S0 UD6  g )N )r   r   super__post_init__)selfkwargs	__class__s     ڀ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/cohere/configuration_cohere.pyr2   CohereConfig.__post_init__W   s-    ##+'+'?'?D$''    )r   ))__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencedefault_thetabase_model_tp_planbase_model_pp_planr   int__annotations__r   r   r   floatr   r   r   r!   strr"   r#   r$   r%   boolr&   r(   r)   listr*   r+   r   dictr,   r-   r.   r2   __static_attributes____classcell__)r5   s   @r6   r
   r
      s   $ J#4"5M%.%.%.%."+ )"+ &(9:#%568IJ!"_$56
 JK"s" &K&s!!&*t*J#'S'#u##'NEDL'It L#*  L#* +1L#S	/D(1 $$48O^d*T18 ND ,/us{T)/$K$( (r8   r
   N)r=   huggingface_hub.dataclassesr   configuration_utilsr   modeling_rope_utilsr   utilsr   r
   __all__r0   r8   r6   <module>rQ      sK   & ! . 3 1 # ;<=(# =(  ==(@ 
r8   