`iYvdZddlmZddlmZddlmZmZeje Z GddeeZ dgZ dS)z6Neighborhood Attention Transformer model configuration)PretrainedConfig)logging)BackboneConfigMixin*get_aligned_output_features_output_indicesc\eZdZdZdZdddZdddgd gd d d d dddddddddffd ZxZS) NatConfiga This is the configuration class to store the configuration of a [`NatModel`]. It is used to instantiate a Nat 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 Nat [shi-labs/nat-mini-in1k-224](https://huggingface.co/shi-labs/nat-mini-in1k-224) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: patch_size (`int`, *optional*, defaults to 4): The size (resolution) of each patch. NOTE: Only patch size of 4 is supported at the moment. num_channels (`int`, *optional*, defaults to 3): The number of input channels. embed_dim (`int`, *optional*, defaults to 64): Dimensionality of patch embedding. depths (`list[int]`, *optional*, defaults to `[3, 4, 6, 5]`): Number of layers in each level of the encoder. num_heads (`list[int]`, *optional*, defaults to `[2, 4, 8, 16]`): Number of attention heads in each layer of the Transformer encoder. kernel_size (`int`, *optional*, defaults to 7): Neighborhood Attention kernel size. mlp_ratio (`float`, *optional*, defaults to 3.0): 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. 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. layer_scale_init_value (`float`, *optional*, defaults to 0.0): The initial value for the layer scale. Disabled if <=0. out_features (`list[str]`, *optional*): If used as backbone, list of features to output. Can be any of `"stem"`, `"stage1"`, `"stage2"`, etc. (depending on how many stages the model has). If unset and `out_indices` is set, will default to the corresponding stages. If unset and `out_indices` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. out_indices (`list[int]`, *optional*): If used as backbone, list of indices of features to output. Can be any of 0, 1, 2, etc. (depending on how many stages the model has). If unset and `out_features` is set, will default to the corresponding stages. If unset and `out_features` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. Example: ```python >>> from transformers import NatConfig, NatModel >>> # Initializing a Nat shi-labs/nat-mini-in1k-224 style configuration >>> configuration = NatConfig() >>> # Initializing a model (with random weights) from the shi-labs/nat-mini-in1k-224 style configuration >>> model = NatModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```nat num_heads num_layers)num_attention_headsnum_hidden_layersr@)rr)rg@Tgg?gelug{Gz?gh㈵>Nc 6tjdi|||_||_||_||_t ||_||_||_ ||_ ||_ | |_ | |_ | |_| |_||_| |_t%|dt |dz zz|_||_dgdt+dt |dzDz|_t/|||j\|_|_dS)Nrstemcg|]}d|S)stage).0idxs /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/deprecated/nat/configuration_nat.py z&NatConfig.__init__..s&Z&Z&Z}s}}&Z&Z&Z) out_features out_indices stage_namesr)super__init__ patch_size num_channels embed_dimdepthslenr r kernel_size mlp_ratioqkv_biashidden_dropout_probattention_probs_dropout_probdrop_path_rate hidden_actlayer_norm_epsinitializer_rangeint hidden_sizelayer_scale_init_valueranger$r _out_features _out_indices)selfr'r(r)r*r r,r-r.r/r0r1r2r4r3r7r"r#kwargs __class__s rr&zNatConfig.__init__ds(* ""6"""$(" f++"&"  #6 ,H),$,!2y1Vq+AABB&<#"8&Z&ZaVWX@Y@Y&Z&Z&ZZ0Z%;DL\1 1 1 -D---r!)__name__ __module__ __qualname____doc__ model_type attribute_mapr& __classcell__)r=s@rrrsA A FJ +)M||--%("%- - - - - - - - - - r!rN) rAconfiguration_utilsrutilsrutils.backbone_utilsrr get_loggerr>loggerr__all__rr!rrKs=<444444dddddddd  H % %x x x x x #%5x x x v -r!