Ë
    ÜÓ^j  ã                   ór   — 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
)é    )Ústricté   )ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringztencent/Youtu-LLM-2B)Ú
checkpointc                   ó$  ‡ — e Zd ZU dZdZdgZddddœZdgdgfd	d
gd	gfd	gd	gfdœZdddddœZi Z	dZ
eed<   dZeed<   dZeed<   dZeed<   dZeed<   dZeed<   dZeed<   dZedz  ed<   d Zeed!<   d"Zedz  ed#<   d"Zeed$<   d%Zeed&<   d'Zeed(<   dZedz  ed)<   d*Zeed+<   d,Zeed-<   dZedz  ed.<   d/Z edz  ed0<   d1Z!ee"e   z  dz  ed2<   d,Z#eed3<   dZ$e%e&z  dz  ed4<   d,Z'edz  ed5<   d6Z(eed7<   d8Z)eez  dz  ed9<   dZ*edz  ed:<   ˆ fd;„Z+ˆ xZ,S )<ÚYoutuConfiga   
    rope_interleave (`bool`, *optional*, defaults to `True`):
        Whether to interleave the rotary position embeddings.
    embedding_initializer_range (`float`, *optional*):
        The standard deviation of the truncated_normal_initializer for initializing all embedding matrices.

    ```python
    >>> from transformers import YoutuModel, YoutuConfig
    >>> # Initializing a Youtu-LLM-2B style configuration
    >>> configuration = YoutuConfig()
    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```ÚyoutuÚpast_key_valuesÚcolwiseÚrowwise)zlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projÚ	input_idsÚinputs_embedsÚhidden_statesÚattention_mask)Úembed_tokensÚlayersÚnormÚ	ep_routerÚgrouped_gemmÚmoe_tp_experts)zlayers.*.mlp.gatez!layers.*.mlp.experts.gate_up_projzlayers.*.mlp.experts.down_projzlayers.*.mlp.expertsi õ Ú
vocab_sizei   Úhidden_sizei   Úintermediate_sizeé    Únum_hidden_layersé   Únum_attention_headsÚnum_key_value_headsi   Úkv_lora_ranki   NÚq_lora_ranké@   Úqk_rope_head_dimé€   Ú
v_head_dimÚqk_nope_head_dimÚsiluÚ
hidden_acti   Úmax_position_embeddingsÚinitializer_rangeg�íµ ÷Æ°>Úrms_norm_epsTÚ	use_cacheÚpad_token_idi ô Úbos_token_idiô Úeos_token_idÚtie_word_embeddingsÚrope_parametersÚrope_interleaveFÚattention_biasg        Úattention_dropoutÚembedding_initializer_rangec                 óz  •— | j                   €1| j                  dk7  rdd| j                  z  dz  z  | _         nd| _         | j                  xs d| j                   z  | _        | j                  €| j                  | _        | j
                  | j                  z   | _        | j                  | _        t        ‰| �(  di |¤Ž y )Nr   g       @g      @g      à?g{®Gáz”?© )r+   r   r6   r    r   r'   r$   Úqk_head_dimÚhead_dimÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €úx/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/youtu/configuration_youtu.pyr<   zYoutuConfig.__post_init__a   s±   ø€ Ø×!Ñ!Ð)Ø×Ñ 1Ò$Ø),°°d×6FÑ6FÑ0FÈ3Ñ/NÑ)N�Õ&à)-�Ô&à+/×+KÑ+KÒ+kÈsÐUY×UkÑUkÑOkˆÔ(Ø×#Ñ#Ð+Ø'+×'?Ñ'?ˆDÔ$à×0Ñ0°4×3HÑ3HÑHˆÔØ×-Ñ-ˆŒÜ‰ÑÑ' Ó'ó    )-Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planÚbase_model_ep_planÚattribute_mapr   ÚintÚ__annotations__r   r   r   r   r    r!   r"   r$   r&   r'   r)   Ústrr*   r+   Úfloatr,   r-   Úboolr.   r/   r0   Úlistr1   r2   r   Údictr3   r4   r5   r6   r<   Ú__classcell__)r?   s   @r@   r
   r
   "   sÇ  ø… ñð €JØ#4Ð"5Ðà"+Ø )Ø"+ñÐð &˜¨Ð(9Ð:Ø#Ð%5Ð6¸Ð8IÐJØ!Ð" _Ð$5Ð6ñÐð )Ø-;Ø*8Ø 0ñ	Ðð €Mà€J�ÓØ€K�ÓØ!Ð�sÓ!ØÐ�sÓØ!Ð˜Ó!Ø!Ð˜Ó!Ø€L�#ÓØ"€K��t‘Ó"ØÐ�cÓØ €J��d‘
Ó ØÐ�cÓØ€J�ÓØ#)Ð˜SÓ)Ø&*Ð�u˜t‘|Ó*Ø€L�%ÓØ€IˆtÓØ#€L�#˜‘*Ó#Ø%€L�#˜‘*Ó%Ø+1€L�#˜˜S™	‘/ DÑ(Ó1Ø $Ð˜Ó$Ø48€O�^ dÑ*¨TÑ1Ó8Ø#'€O�T˜D‘[Ó'Ø €N�DÓ Ø,/Ð�u˜s‘{ TÑ)Ó/Ø04Ð ¨¡Ó4÷(ð (rA   r
   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r8   rA   r@   ú<module>rY      sJ   ðõ6 /å 3Ý 1Ý #ñ Ð1Ô2ØôJ(Ð"ó J(ó ó 3ðJ(ðZ ˆ/�rA   