ó
    qyüi  ã                   ód   • 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mT5 model configurationé    )Ústricté   )ÚPreTrainedConfig)Úauto_docstringzgoogle/mt5-small)Ú
checkpointc                   ó¶  ^ • \ rS rSr% SrSrS/r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'   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$'   S%r\	S-  \
S&'   S'r\	\ \	   -  S-  \
S('   S%r!\	S-  \
S)'   S*r"\\	-  \
S+'   S,r#\\
S-'   U 4S. jr$S/ r%S0r&U =r'$ )1Ú	MT5Configé   a­  
relative_attention_num_buckets (`int`, *optional*, defaults to 32):
    The number of buckets to use for each attention layer.
relative_attention_max_distance (`int`, *optional*, defaults to 128):
    The maximum distance of the longer sequences for the bucket separation.
feed_forward_proj (`str`, *optional*, defaults to `"gated-gelu"`):
    Type of feed forward layer to be used. Should be one of `"relu"` or `"gated-gelu"`.
Úmt5Úpast_key_valuesÚd_modelÚ	num_headsÚ
num_layersÚd_kv)Úhidden_sizeÚnum_attention_headsÚnum_hidden_layersÚhead_dimi Ñ Ú
vocab_sizei   é@   i   Úd_ffé   NÚnum_decoder_layersé   é    Úrelative_attention_num_bucketsé€   Úrelative_attention_max_distancegš™™™™™¹?Údropout_rateg�íµ ÷Æ°>Úlayer_norm_epsilong      ð?Úinitializer_factorú
gated-geluÚfeed_forward_projTÚis_encoder_decoderÚ	use_cacheÚtie_word_embeddingsÚbos_token_idr   Úpad_token_idé   Úeos_token_idÚdecoder_start_token_idg        Úclassifier_dropoutFÚ
is_decoderc                 ó>  >• U R                   b  U R                   OU R                  U l         U R                  R                  S5      nUS   U l        US   S:H  U l        U R                  S:X  a  SU l        UR                  SS 5        SU l        [        TU ]$  " S	0 UD6  g )
NÚ-éÿÿÿÿr   Úgatedr"   Úgelu_newr&   T© )
r   r   r#   ÚsplitÚdense_act_fnÚis_gated_actÚpopr&   ÚsuperÚ__post_init__)ÚselfÚkwargsÚact_infoÚ	__class__s      €Úf/home/mande/repo/quber/.venv/lib/python3.13/site-packages/transformers/models/mt5/configuration_mt5.pyr9   ÚMT5Config.__post_init__B   sœ   ø€ à'+×'>Ñ'>Ñ'JˆD×#Ò#ÐPT×P_ÑP_ð 	Ôð ×)Ñ)×/Ñ/°Ó4ˆØ$ R™LˆÔØ$ Q™K¨7Ñ2ˆÔà×!Ñ! \Ó1Ø *ˆDÔð 	�
‰
Ð(¨$Ô/Ø#'ˆÔ Ü‰ÒÑ' Ó'ó    c                 óº   • U R                   R                  S5      n[        U5      S:”  a	  US   S:w  d  [        U5      S:”  a  [        SU R                    S35      eg)	zOPart of `@strict`-powered validation. Validates the architecture of the config.r/   r)   r   r1   é   z`feed_forward_proj`: z© is not a valid activation function of the dense layer. Please make sure `feed_forward_proj` is of the format `gated-{ACT_FN}` or `{ACT_FN}`, e.g. 'gated-gelu' or 'relu'N)r#   r4   ÚlenÚ
ValueError)r:   r<   s     r>   Úvalidate_architectureÚMT5Config.validate_architectureS   sf   € à×)Ñ)×/Ñ/°Ó4ˆäˆx‹=˜1Ó ¨!¡°Ó!7¼3¸x»=È1Ó;LÜØ'¨×(>Ñ(>Ð'?ð @)ð )óð ð <Mr@   )r5   r6   r   r&   )(Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚattribute_mapr   ÚintÚ__annotations__r   r   r   r   r   r   r   r   r   Úfloatr    r!   r#   Ústrr$   Úboolr%   r&   r'   r(   r*   Úlistr+   r,   r-   r9   rE   Ú__static_attributes__Ú__classcell__)r=   s   @r>   r	   r	      sF  ø‡ ñð €JØ#4Ð"5Ðà Ø*Ø)Øñ	€Mð €J�ÓØ€GˆSÓØ€Dˆ#ƒNØ€Dˆ#ÓØ€J�ÓØ%)Ð˜˜d™
Ó)Ø€IˆsÓØ*,Ð" CÓ,Ø+.Ð# SÓ.Ø #€L�%˜#‘+Ó#Ø $Ð˜Ó$Ø #Ð˜Ó#Ø)Ð�sÓ)Ø#Ð˜Ó#Ø€IˆtÓØ $Ð˜Ó$Ø#€L�#˜‘*Ó#Ø €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø)*Ð˜C $™JÓ*Ø&)Ð˜ ™Ó)Ø€J�Óõ(÷"	ð 	r@   r	   N)	rK   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r	   Ú__all__r3   r@   r>   Ú<module>r[      sJ   ðñ å .å 3Ý #ñ Ð-Ñ.ØôDÐ ó Dó ó /ðDðN ˆ-�r@   