^jjdZddlmZddlmZddlmZedeGdd eZd gZy ) zCvT model configuration)strict)PreTrainedConfig)auto_docstringzmicrosoft/cvt-13) checkpointceZdZUdZdZdZeed<dZe ee edfzed<dZ e ee edfzed <d Z e ee edfzed <d Z e ee edfzed <dZe ee edfzed<dZe ee edfzed<dZe ee edfzed<dZe ee edfzed<dZe ee edfzed<dZe ee edfzed<dZe ee edfzed<dZe ee edfzed<dZe ee edfzed<dZe ee edfzed <d!Ze ee edfzed"<d#Ze ee edfzed$<d!Ze ee edfzed%<d!Ze ee edfzed&<d'Zeed(<d)Z eed*<y+), CvtConfiga9 patch_stride (`list[int]`, *optional*, defaults to `[4, 2, 2]`): The stride size of each encoder's patch embedding. patch_padding (`list[int]`, *optional*, defaults to `[2, 1, 1]`): The padding size of each encoder's patch embedding. depth (`list[int]`, *optional*, defaults to `[1, 2, 10]`): The number of layers in each encoder block. attention_drop_rate (`list[float]`, *optional*, defaults to `[0.0, 0.0, 0.0]`): The dropout ratio for the attention probabilities. drop_rate (`list[float]`, *optional*, defaults to `[0.0, 0.0, 0.0]`): The dropout ratio for the patch embeddings probabilities. cls_token (`list[bool]`, *optional*, defaults to `[False, False, True]`): Whether or not to add a classification token to the output of each of the last 3 stages. qkv_projection_method (`list[string]`, *optional*, defaults to ["dw_bn", "dw_bn", "dw_bn"]`): The projection method for query, key and value Default is depth-wise convolutions with batch norm. For Linear projection use "avg". kernel_qkv (`list[int]`, *optional*, defaults to `[3, 3, 3]`): The kernel size for query, key and value in attention layer padding_kv (`list[int]`, *optional*, defaults to `[1, 1, 1]`): The padding size for key and value in attention layer stride_kv (`list[int]`, *optional*, defaults to `[2, 2, 2]`): The stride size for key and value in attention layer padding_q (`list[int]`, *optional*, defaults to `[1, 1, 1]`): The padding size for query in attention layer stride_q (`list[int]`, *optional*, defaults to `[1, 1, 1]`): The stride size for query in attention layer Example: ```python >>> from transformers import CvtConfig, CvtModel >>> # Initializing a Cvt msft/cvt style configuration >>> configuration = CvtConfig() >>> # Initializing a model (with random weights) from the msft/cvt style configuration >>> model = CvtModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```cvtr num_channels)rr. patch_sizes)r patch_stride)rr patch_padding)@i embed_dim)rr num_heads)rr depth)@rr mlp_ratio)rrattention_drop_rate drop_rate)rrg?drop_path_rate)TTTqkv_bias)FFT cls_token)dw_bnr"r"qkv_projection_method)rrr kernel_qkv)rrr padding_kv)rrr stride_kv padding_qstride_qg{Gz?initializer_rangeg-q=layer_norm_epsN)!__name__ __module__ __qualname____doc__ model_typer int__annotations__r listtuplerrrrrrfloatrrrr boolr!r#strr$r%r&r'r(r)r*t/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/cvt/configuration_cvt.pyr r s( TJL#/8KcU38_,809L$s)eCHo-91:M49uS#X.:-;ItCy5c?*;-6ItCy5c?*6)3E49uS#X &31@ItE{U5#:..@;JeuUCZ'88J1@ItE{U5#:..@6ENDK%s "33E.@Hd4j5s++@/CItDzE$),,C9T49uS#X6T.7JS E#s(O+7.7JS E#s(O+7-6ItCy5c?*6-6ItCy5c?*6,5Hd3i%S/)5#u#!NE!r8r N) r.huggingface_hub.dataclassesrconfiguration_utilsrutilsrr __all__r7r8r9r>sJ.3#-.A" A"/A"H -r8