o i@s@dZddlmZddlmZeeZGdddeZdgZ dS)z*Donut Swin Transformer model configuration)PretrainedConfig)loggingcsXeZdZdZdZdddZdddd gd gd d d ddddddddffdd ZZS)DonutSwinConfiga This is the configuration class to store the configuration of a [`DonutSwinModel`]. It is used to instantiate a Donut 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 Donut [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) 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 (resolution) of each image. patch_size (`int`, *optional*, defaults to 4): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. embed_dim (`int`, *optional*, defaults to 96): Dimensionality of patch embedding. depths (`list(int)`, *optional*, defaults to `[2, 2, 6, 2]`): Depth of each layer in the Transformer encoder. num_heads (`list(int)`, *optional*, defaults to `[3, 6, 12, 24]`): Number of attention heads in each layer of the Transformer encoder. window_size (`int`, *optional*, defaults to 7): Size of windows. mlp_ratio (`float`, *optional*, defaults to 4.0): Ratio of MLP hidden dimensionality to embedding dimensionality. qkv_bias (`bool`, *optional*, defaults to `True`): Whether or not a learnable bias should be added to the queries, keys and values. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings and encoder. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. drop_path_rate (`float`, *optional*, defaults to 0.1): Stochastic depth rate. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. use_absolute_embeddings (`bool`, *optional*, defaults to `False`): Whether or not to add absolute position embeddings to the patch embeddings. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. Example: ```python >>> from transformers import DonutSwinConfig, DonutSwinModel >>> # Initializing a Donut naver-clova-ix/donut-base style configuration >>> configuration = DonutSwinConfig() >>> # Randomly initializing a model from the naver-clova-ix/donut-base style configuration >>> model = DonutSwinModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```z donut-swin num_heads num_layers)num_attention_headsnum_hidden_layersr`)r r )rr g@Tgg?geluFg{Gz?gh㈵>c stjdi|||_||_||_||_||_t||_||_ ||_ ||_ | |_ | |_ | |_| |_| |_||_||_||_t|dt|d|_dS)Nr )super__init__ image_size patch_size num_channels embed_dimdepthslenrr window_size mlp_ratioqkv_biashidden_dropout_probattention_probs_dropout_probdrop_path_rate hidden_actuse_absolute_embeddingslayer_norm_epsinitializer_rangeint hidden_size)selfrrrrrrrrrrr r!r"r#r%r$kwargs __class__rf/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/donut/configuration_donut_swin.pyr[s& zDonutSwinConfig.__init__)__name__ __module__ __qualname____doc__ model_type attribute_mapr __classcell__rrr*r,rs.;rN) r0configuration_utilsrutilsr get_loggerr-loggerr__all__rrrr,s     o