
    Z j                     d    S 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OPT model configuration    )strict   )PreTrainedConfig)auto_docstringzfacebook/opt-350m)
checkpointc                     ^  \ rS rSr% SrSr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'   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r!\\	S''   U 4S( jr"S)r#U =r$$ )*	OPTConfig   a  
do_layer_norm_before (`bool`, *optional*, defaults to `True`):
    Whether to perform layer normalization before the attention block.
word_embed_proj_dim (`int`, *optional*):
    `word_embed_proj_dim` can be set to down-project word embeddings, *e.g.* `opt-350m`. Defaults to
    `hidden_size`.
enable_bias (`bool`, *optional*, defaults to `True`):
    Whether or not if the linear layers in the attention blocks should use the bias term.
layer_norm_elementwise_affine (`bool`, *optional*, defaults to `True`):
    Whether or not if the layer norms should have learnable parameters.

Example:

```python
>>> from transformers import OPTConfig, OPTModel

>>> # Initializing a OPT facebook/opt-large style configuration
>>> configuration = OPTConfig()

>>> # Initializing a model (with random weights) from the facebook/opt-large style configuration
>>> model = OPTModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```optpast_key_valuesi`  
vocab_sizei   hidden_size   num_hidden_layersi   ffn_dimi   max_position_embeddingsTdo_layer_norm_beforeF_remove_final_layer_normNword_embed_proj_dimg?dropoutg        attention_dropoutnum_attention_headsreluactivation_function	layerdropg{Gz?init_std	use_cache   pad_token_id   bos_token_ideos_token_idenable_biaslayer_norm_elementwise_affinetie_word_embeddingsc                 z   > U R                   b  U R                   OU R                  U l         [        TU ]  " S0 UD6  g )N )r   r   super__post_init__)selfkwargs	__class__s     z/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/opt/configuration_opt.pyr)   OPTConfig.__post_init__L   s:    (,(@(@(LD$$RVRbRb 	  	''    )r   )%__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencer   int__annotations__r   r   r   r   r   boolr   r   r   floatr   r   r   strr   r   r   r   r!   r"   listr#   r$   r%   r)   __static_attributes____classcell__)r,   s   @r-   r	   r	      s#   4 J#4"5JKsGS#'S'!%$%%*d*&*t*GUS[%(us{(!!%% Ius{ HeIt L#*  L#* +,L#S	/D(,K*.!4. $$( (r/   r	   N)	r4   huggingface_hub.dataclassesr   configuration_utilsr   utilsr   r	   __all__r'   r/   r-   <module>rC      sG     . 3 # ./8(  8(  08(v -r/   