
    Z j                     |    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 configuration    )strict   )%consolidate_backbone_kwargs_to_config)PreTrainedConfig)auto_docstring   )
AutoConfigzIntel/tvp-base)
checkpointc                     ^  \ 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'$ )/	TvpConfig   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.
tvpbackbone_configNg      ?distance_loss_weightg?duration_loss_weightframepadvisual_prompter_typereplacevisual_prompter_apply`   visual_prompt_sizei  max_img_size0   
num_framesi:w  
vocab_sizer   type_vocab_sizei   hidden_sizei   intermediate_size   num_hidden_layersnum_attention_headsi   max_position_embeddingsd    max_grid_col_position_embeddings max_grid_row_position_embeddingshidden_dropout_probgelu
hidden_actg-q=layer_norm_epsg{Gz?initializer_rangeattention_probs_dropout_probpad_token_idc                 n   > [        SU R                  SSS/0S.UD6u  U l        n[        TU ]  " S0 UD6  g )Nresnetout_featuresstage4)r   default_config_typedefault_config_kwargs )r   r   super__post_init__)selfkwargs	__class__s     z/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/tvp/configuration_tvp.pyr5   TvpConfig.__post_init__P   sL    'L (
 00 (#1H:">(
 	(
$f 	''    )r   )(__name__
__module____qualname____firstlineno____doc__
model_typer	   sub_configsr   dictr   __annotations__r   floatr   r   strr   r   intr   r   r   r   r   r   r    r!   r"   r$   r%   r&   r(   r)   r*   r+   r,   r5   __static_attributes____classcell__)r8   s   @r9   r   r      s.   4 J$j1K6:OT,,t3:"%%%"%%% *#*!*3*  L#JJOSK!s!s!!#&S&,/$c/,/$c/'**J!NE!#u#03 %#+3#L#*#( (r;   r   N)r@   huggingface_hub.dataclassesr   backbone_utilsr   configuration_utilsr   utilsr   autor	   r   __all__r3   r;   r9   <module>rP      sM     . C 3 #  +,>(  >(  ->(B -r;   