
    Z jm                     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YOSO model configuration    )strict   )PreTrainedConfig)auto_docstringzuw-madison/yoso-4096)
checkpointc                      \ 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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$'   S%r\S -  \S&'   S'r\\ \   -  S -  \S('   S)r!\\S*'   Sr"\\S+'   S,r#g )-
YosoConfig   aY  
use_expectation (`bool`, *optional*, defaults to `True`):
    Whether or not to use YOSO Expectation. Overrides any effect of num_hash.
hash_code_len (`int`, *optional*, defaults to 9):
    The length of hashes generated by the hash functions.
num_hash (`int`, *optional*, defaults to 64):
    Number of hash functions used in [`YosoSelfAttention`].
conv_window (`int`, *optional*):
    Kernel size of depth-wise convolution.
use_fast_hash (`bool`, *optional*, defaults to `False`):
    Whether or not to use custom cuda kernels which perform fast random projection via hadamard transform.
lsh_backward (`bool`, *optional*, defaults to `True`):
    Whether or not to perform backpropagation using Locality Sensitive Hashing.

Example:

```python
>>> from transformers import YosoConfig, YosoModel

>>> # Initializing a YOSO uw-madison/yoso-4096 style configuration
>>> configuration = YosoConfig()

>>> # Initializing a model (with random weights) from the uw-madison/yoso-4096 style configuration
>>> model = YosoModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```yosoiY  
vocab_sizei   hidden_size   num_hidden_layersnum_attention_headsi   intermediate_sizegelu
hidden_actg?hidden_dropout_probattention_probs_dropout_probi   max_position_embeddings   type_vocab_sizeg{Gz?initializer_rangeg-q=layer_norm_epsTuse_expectation	   hash_code_len@   num_hashNconv_windowuse_fast_hashlsh_backwardpad_token_idr   bos_token_id   eos_token_idFadd_cross_attentiontie_word_embeddings )$__name__
__module____qualname____firstlineno____doc__
model_typer   int__annotations__r   r   r   r   r   strr   floatr   r   r   r   r   r   boolr   r   r    r!   r"   r#   r$   r&   listr'   r(   __static_attributes__r)       |/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/yoso/configuration_yoso.pyr	   r	      s   : JJKs!!!s!J'**03 %#+3#'S'OS#u#!NE! OT M3Hc"Kt"M4L$ L#*  L#* +,L#S	/D(, %% $$r7   r	   N)	r.   huggingface_hub.dataclassesr   configuration_utilsr   utilsr   r	   __all__r)   r7   r8   <module>r=      sG     . 3 # 126%! 6%  36%r .r7   