ó
    qyüiÚ  ã                   ó|   • S r SSKJr  SSKJ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TVP model configurationé    )Ústricté   )Ú%consolidate_backbone_kwargs_to_config)ÚPreTrainedConfig)Úauto_docstringé   )Ú
AutoConfigzIntel/tvp-base)Ú
checkpointc                   óš  ^ • \ rS rSr% SrSrS\0r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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,'   U 4S- jr%S.r&U =r'$ )/Ú	TvpConfigé   ap  
distance_loss_weight (`float`, *optional*, defaults to 1.0):
    The weight of distance loss.
duration_loss_weight (`float`, *optional*, defaults to 0.1):
    The weight of duration loss.
visual_prompter_type (`str`, *optional*, defaults to `"framepad"`):
    Visual prompt type. The type of padding. Framepad means padding on each frame. Should be one of "framepad"
    or "framedownpad"
visual_prompter_apply (`str`, *optional*, defaults to `"replace"`):
    The way of applying visual prompt. Replace means use the value of prompt to change the original value in
    visual inputs. Should be one of "replace", or "add", or "remove".
visual_prompt_size (`int`, *optional*, defaults to 96):
    The size of visual prompt.
max_img_size (`int`, *optional*, defaults to 448):
    The maximum size of frame.
num_frames (`int`, *optional*, defaults to 48):
    The number of frames extracted from a video.
max_position_embeddings (`int`, *optional*, defaults to 512):
    The maximum sequence length that this model might ever be used with. Typically set this to something large
    just in case (e.g., 512 or 1024 or 2048).
max_grid_col_position_embeddings (`int`, *optional*, defaults to 100):
    The largest number of horizontal patches from a video frame.
max_grid_row_position_embeddings (`int`, *optional*, defaults to 100):
    The largest number of vertical patches from a video frame.
ÚtvpÚbackbone_configNg      ð?Údistance_loss_weightgš™™™™™¹?Úduration_loss_weightÚframepadÚvisual_prompter_typeÚreplaceÚvisual_prompter_applyé`   Úvisual_prompt_sizeiÀ  Úmax_img_sizeé0   Ú
num_framesi:w  Ú
vocab_sizer   Útype_vocab_sizei   Úhidden_sizei   Úintermediate_sizeé   Únum_hidden_layersÚnum_attention_headsi   Úmax_position_embeddingséd   Ú max_grid_col_position_embeddingsÚ max_grid_row_position_embeddingsÚhidden_dropout_probÚgeluÚ
hidden_actgê-�™—q=Úlayer_norm_epsg{®Gáz”?Úinitializer_rangeÚattention_probs_dropout_probÚpad_token_idc                 ón   >• [        SU R                  SSS/0S.UD6u  U l        n[        TU ]  " S0 UD6  g )NÚresnetÚout_featuresÚstage4)r   Údefault_config_typeÚdefault_config_kwargs© )r   r   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €Úf/home/mande/repo/quber/.venv/lib/python3.13/site-packages/transformers/models/tvp/configuration_tvp.pyr5   ÚTvpConfig.__post_init__P   sL   ø€ Ü'Lð (
Ø ×0Ñ0Ø (Ø#1°H°:Ð">ñ(
ð ñ	(
Ñ$ˆÔ˜fô 	‰ÒÑ' Ó'ó    )r   )(Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typer	   Úsub_configsr   Údictr   Ú__annotations__r   Úfloatr   r   Ústrr   r   Úintr   r   r   r   r   r   r    r!   r"   r$   r%   r&   r(   r)   r*   r+   r,   r5   Ú__static_attributes__Ú__classcell__)r8   s   @r9   r   r      s.  ø‡ ñð4 €JØ$ jÐ1€Kà6:€O�TÐ,Ñ,¨tÑ3Ó:Ø"%Ð˜%Ó%Ø"%Ð˜%Ó%Ø *Ð˜#Ó*Ø!*Ð˜3Ó*Ø Ð˜Ó Ø€L�#ÓØ€J�ÓØ€J�ÓØ€O�SÓØ€K�ÓØ!Ð�sÓ!ØÐ�sÓØ!Ð˜Ó!Ø#&Ð˜SÓ&Ø,/Ð$ cÓ/Ø,/Ð$ cÓ/Ø'*Ð˜ ™Ó*Ø€J�ÓØ!€N�EÓ!Ø#Ð�uÓ#Ø03Ð  %¨#¡+Ó3Ø#€L�#˜‘*Ó#÷(ó (r;   r   N)r@   Úhuggingface_hub.dataclassesr   Úbackbone_utilsr   Úconfiguration_utilsr   Úutilsr   Úautor	   r   Ú__all__r3   r;   r9   Ú<module>rP      sM   ðñ å .å CÝ 3Ý #Ý ñ Ð+Ñ,Øô>(Ð ó >(ó ó -ð>(ðB ˆ-�r;   