Ë
    ÜÓ^jò	  ã                   óv   — d Z ddlmZ ddlmZ ddlmZ ddlmZ  ed¬«      e G d	„ d
e«      «       «       Z	d
gZ
y)zStableLM model configurationé    )Ústricté   )ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzstabilityai/stablelm-3b-4e1t)Ú
checkpointc                   óŠ  ‡ — e Zd ZU dZdZdgZdZeed<   dZ	eed<   dZ
eed	<   d
Zeed<   d
Zeed<   d
Zeed<   dZeed<   dZeed<   dZeed<   dZeed<   dZeed<   dZeed<   dZeez  dz  ed<   dZeed<   dZeed<   dZeed<   dZeez  ed <   dZeez  ed!<   d"Zedz  ed#<   d"Z ee!e   z  dz  ed$<   dZ"edz  ed%<   ˆ fd&„Z#ˆ xZ$S )'ÚStableLmConfiga'  
    use_parallel_residual (`bool`, *optional*, defaults to `False`):
        Whether to use a "parallel" formulation in each Transformer layer, which can provide a slight training
        speedup at large scales.
    hidden_dropout (`float`, *optional*, defaults to 0.0):
        The dropout ratio after applying the MLP to the hidden states.

    Example:

    ```python
    >>> from transformers import StableLmModel, StableLmConfig

    >>> # Initializing a StableLM stablelm-3b style configuration
    >>> configuration = StableLmConfig()
    ```ÚstablelmÚpast_key_valuesi€Ä  Ú
vocab_sizei   Úintermediate_sizei 
  Úhidden_sizeé    Únum_hidden_layersÚnum_attention_headsÚnum_key_value_headsÚsiluÚ
hidden_acti   Úmax_position_embeddingsg{®Gáz”?Úinitializer_rangegñhãˆµøä>Úlayer_norm_epsTÚ	use_cacheFÚtie_word_embeddingsNÚrope_parametersÚuse_qkv_biasÚqk_layernormÚuse_parallel_residualg        Úhidden_dropoutÚattention_dropoutr   Úbos_token_idÚeos_token_idÚpad_token_idc                 óH   •— |j                  dd«       t        ‰| �  di |¤Ž y )NÚpartial_rotary_factorg      Ð?© )Ú
setdefaultÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €ú~/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/stablelm/configuration_stablelm.pyr)   zStableLmConfig.__post_init__C   s$   ø€ Ø×ÑÐ1°4Ô8Ü‰ÑÑ' Ó'ó    )%Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferencer   ÚintÚ__annotations__r   r   r   r   r   r   Ústrr   r   Úfloatr   r   Úboolr   r   r   Údictr   r   r   r   r    r!   r"   Úlistr#   r)   Ú__classcell__)r,   s   @r-   r
   r
      s$  ø… ñð  €JØ#4Ð"5Ðà€J�ÓØ!Ð�sÓ!Ø€K�ÓØÐ�sÓØ!Ð˜Ó!Ø!Ð˜Ó!Ø€J�ÓØ#'Ð˜SÓ'Ø#Ð�uÓ#Ø"€N�EÓ"Ø€IˆtÓØ %Ð˜Ó%Ø48€O�^ dÑ*¨TÑ1Ó8Ø€L�$ÓØ€L�$ÓØ"'Ð˜4Ó'Ø"%€N�E˜C‘KÓ%Ø%(Ð�u˜s‘{Ó(Ø €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø#€L�#˜‘*Ó#÷(ð (r.   r
   N)r2   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r&   r.   r-   ú<module>rB      sK   ðñ #å .å 3Ý 1Ý #ñ Ð9Ô:Øô,(Ð%ó ,(ó ó ;ð,(ð^ Ð
�r.   