
    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LED model configuration    )strict   )PreTrainedConfig)auto_docstringzallenai/led-base-16384)
checkpointc                      \ rS rSr% SrSrSSSSS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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'g')0	LEDConfig   a  
max_encoder_position_embeddings (`int`, *optional*, defaults to 16384):
    The maximum sequence length that the encoder might ever be used with.
max_decoder_position_embeddings (`int`, *optional*, defaults to 16384):
    The maximum sequence length that the decoder might ever be used with.
attention_window (`int` or `list[int]`, *optional*, defaults to 512):
    Size of an attention window around each token. If an `int`, use the same size for all layers. To specify a
    different window size for each layer, use a `list[int]` where `len(attention_window) == num_hidden_layers`.

Example:

```python
>>> from transformers import LEDModel, LEDConfig

>>> # Initializing a LED allenai/led-base-16384 style configuration
>>> configuration = LEDConfig()

>>> # Initializing a model from the allenai/led-base-16384 style configuration
>>> model = LEDModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```ledencoder_attention_headsd_modelattention_dropoutinit_stdencoder_layers)num_attention_headshidden_sizeattention_probs_dropout_probinitializer_rangenum_hidden_layersiY  
vocab_sizei @  max_encoder_position_embeddingsi   max_decoder_position_embeddings   i   encoder_ffn_dim   decoder_layersdecoder_ffn_dimdecoder_attention_headsg        encoder_layerdropdecoder_layerdropT	use_cacheis_encoder_decodergeluactivation_functiong?dropoutactivation_dropoutg{Gz?   decoder_start_token_idclassifier_dropout   Npad_token_idr   bos_token_ideos_token_idi   attention_windowtie_word_embeddings )(__name__
__module____qualname____firstlineno____doc__
model_typeattribute_mapr   int__annotations__r   r   r   r   r   r   r   r   r   floatr    r!   boolr"   r$   strr   r%   r   r&   r   r(   r)   r+   r,   r-   listr.   r/   __static_attributes__r0       z/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/led/configuration_led.pyr	   r	      sm   0 J8 (;'-M J+0#S0+/#S/NCOS#%S%NCOS#%S%%(us{(%(us{(It##%%GSGUS[%(us{(&))He"#C#&)) L#*  L#* +,L#S	/D(,(+d3i#o+ $$r?   r	   N)	r5   huggingface_hub.dataclassesr   configuration_utilsr   utilsr   r	   __all__r0   r?   r@   <module>rE      sG     . 3 # 34;%  ;%  5;%| -r?   