
    Z js                     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MobileBERT model configuration    )strict   )PreTrainedConfig)auto_docstringzgoogle/mobilebert-uncased)
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'   Sr\\S'   Sr\\S '   Sr\\S!'   Sr\\S"'   S#r\\S$'   Sr\\S%'   S
r\\S&'   S'r\\S('   Sr \\S)'   Sr!\\-  S-  \S*'   Sr"\\S+'   U 4S, jr#S-r$U =r%$ ).MobileBertConfig   a  
embedding_size (`int`, *optional*, defaults to 128):
    The dimension of the word embedding vectors.
trigram_input (`bool`, *optional*, defaults to `True`):
    Use a convolution of trigram as input.
use_bottleneck (`bool`, *optional*, defaults to `True`):
    Whether to use bottleneck in BERT.
intra_bottleneck_size (`int`, *optional*, defaults to 128):
    Size of bottleneck layer output.
use_bottleneck_attention (`bool`, *optional*, defaults to `False`):
    Whether to use attention inputs from the bottleneck transformation.
key_query_shared_bottleneck (`bool`, *optional*, defaults to `True`):
    Whether to use the same linear transformation for query&key in the bottleneck.
num_feedforward_networks (`int`, *optional*, defaults to 4):
    Number of FFNs in a block.
normalization_type (`str`, *optional*, defaults to `"no_norm"`):
    The normalization type in MobileBERT.

Examples:

```python
>>> from transformers import MobileBertConfig, MobileBertModel

>>> # Initializing a MobileBERT configuration
>>> configuration = MobileBertConfig()

>>> # Initializing a model (with random weights) from the configuration above
>>> model = MobileBertModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```

mobileberti:w  
vocab_sizei   hidden_size   num_hidden_layers   num_attention_headsintermediate_sizerelu
hidden_actg        hidden_dropout_probg?attention_probs_dropout_probmax_position_embeddings   type_vocab_sizeg{Gz?initializer_rangeg-q=layer_norm_epsr   Npad_token_id   embedding_sizeTtrigram_inputuse_bottleneckintra_bottleneck_sizeFuse_bottleneck_attentionkey_query_shared_bottlenecknum_feedforward_networksno_normnormalization_typeclassifier_activationclassifier_dropouttie_word_embeddingsc                    > U R                   (       a  U R                  U l        OU R                  U l        [        TU ]  " S0 UD6  g )N )r    r!   true_hidden_sizer   super__post_init__)selfkwargs	__class__s     ڈ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/mobilebert/configuration_mobilebert.pyr.   MobileBertConfig.__post_init__V   s8    $($>$>D!$($4$4D!''    )r,   )&__name__
__module____qualname____firstlineno____doc__
model_typer   int__annotations__r   r   r   r   r   strr   floatr   r   r   r   r   r   r   r   boolr    r!   r"   r#   r$   r&   r'   r(   r)   r.   __static_attributes____classcell__)r1   s   @r2   r	   r	      s.    D JJKs   s J'**03 %#+3#&S&OS#u#!NE! L#* NCM4ND!$3$%*d*(,,$%c%''"&4&-1d*1 $$( (r4   r	   N)	r9   huggingface_hub.dataclassesr   configuration_utilsr   utilsr   r	   __all__r+   r4   r2   <module>rF      sK    % . 3 # 67C(' C(  8C(L 
r4   