o Û·iŒã@s‚dZddlmZddlmZddlmZddlmZddl m Z ddl m Z e   e¡ZGd d „d eƒZGd d „d e ƒZd d gZd S)zLeViT model configurationé©Ú OrderedDict)ÚMapping)Úversioné)ÚPretrainedConfig)Ú OnnxConfig)ÚloggingcsZeZdZdZdZddddddgd¢gd ¢gd ¢gd ¢d gd ¢gd ¢df‡fdd„ Z‡ZS)Ú LevitConfigaÇ This is the configuration class to store the configuration of a [`LevitModel`]. It is used to instantiate a LeViT model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the LeViT [facebook/levit-128S](https://huggingface.co/facebook/levit-128S) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: image_size (`int`, *optional*, defaults to 224): The size of the input image. num_channels (`int`, *optional*, defaults to 3): Number of channels in the input image. kernel_size (`int`, *optional*, defaults to 3): The kernel size for the initial convolution layers of patch embedding. stride (`int`, *optional*, defaults to 2): The stride size for the initial convolution layers of patch embedding. padding (`int`, *optional*, defaults to 1): The padding size for the initial convolution layers of patch embedding. patch_size (`int`, *optional*, defaults to 16): The patch size for embeddings. hidden_sizes (`list[int]`, *optional*, defaults to `[128, 256, 384]`): Dimension of each of the encoder blocks. num_attention_heads (`list[int]`, *optional*, defaults to `[4, 8, 12]`): Number of attention heads for each attention layer in each block of the Transformer encoder. depths (`list[int]`, *optional*, defaults to `[4, 4, 4]`): The number of layers in each encoder block. key_dim (`list[int]`, *optional*, defaults to `[16, 16, 16]`): The size of key in each of the encoder blocks. drop_path_rate (`int`, *optional*, defaults to 0): The dropout probability for stochastic depths, used in the blocks of the Transformer encoder. mlp_ratios (`list[int]`, *optional*, defaults to `[2, 2, 2]`): Ratio of the size of the hidden layer compared to the size of the input layer of the Mix FFNs in the encoder blocks. attention_ratios (`list[int]`, *optional*, defaults to `[2, 2, 2]`): Ratio of the size of the output dimension compared to input dimension of attention layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Example: ```python >>> from transformers import LevitConfig, LevitModel >>> # Initializing a LeViT levit-128S style configuration >>> configuration = LevitConfig() >>> # Initializing a model (with random weights) from the levit-128S style configuration >>> model = LevitModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Úlevitéàrééé)é€éi€)ééé )rrr)rrrr)r r r g{®Gáz”?c s¬tƒjdi|¤Ž||_||_||_||_||_||_||_| |_ | |_ | |_ ||_ | |_ | |_||_d| d|d| ddddgd| d|d| ddddgg|_dS)NÚ Subsamplerrr r©)ÚsuperÚ__init__Ú image_sizeÚ num_channelsÚ kernel_sizeÚstrideÚpaddingÚ hidden_sizesÚnum_attention_headsÚdepthsÚkey_dimÚdrop_path_rateÚ patch_sizeÚattention_ratioÚ mlp_ratioÚinitializer_rangeÚdown_ops)Úselfrrrrrr#rrr r!r"r%r$r&Úkwargs©Ú __class__rúc/home/ubuntu/vllm_env/lib/python3.10/site-packages/transformers/models/levit/configuration_levit.pyrXs$ þzLevitConfig.__init__)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typerÚ __classcell__rrr*r,r s$7ñr c@sJeZdZe d¡Zedeeee efffdd„ƒZ ede fdd„ƒZ dS)ÚLevitOnnxConfigz1.11ÚreturncCstddddddœfgƒS)NÚ pixel_valuesÚbatchrÚheightÚwidth)rrr rr©r(rrr,ÚinputsƒsÿÿzLevitOnnxConfig.inputscCsdS)Ng-Cëâ6?rr9rrr,Úatol_for_validation‹sz#LevitOnnxConfig.atol_for_validationN) r-r.r/rÚparseÚtorch_onnx_minimum_versionÚpropertyrÚstrÚintr:Úfloatr;rrrr,r3€s   r3N)r0Ú collectionsrÚcollections.abcrÚ packagingrÚconfiguration_utilsrÚonnxrÚutilsr Ú get_loggerr-Úloggerr r3Ú__all__rrrr,Ús       b