qi:ddlmZddlmZGddeeZdgZy))BackboneConfigMixin)PreTrainedConfigcNeZdZdZdZ dfd ZxZS) PixioConfiga This is the configuration class to store the configuration of a [`PixioModel`]. It is used to instantiate a Pixio 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 ViT [facebook/pixio-huge](https://huggingface.co/facebook/pixio-huge) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 1280): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 32): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. mlp_ratio (`int`, *optional*, defaults to 4): Ratio of the hidden size of the MLPs relative to the `hidden_size`. n_cls_tokens (`int`, *optional*, defaults to 8): Number of class tokens in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. 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-06): The epsilon used by the layer normalization layers. image_size (`int`, *optional*, defaults to 256): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. drop_path_rate (`float`, *optional*, defaults to 0.0): Stochastic depth rate per sample (when applied in the main path of residual layers). 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. apply_layernorm (`bool`, *optional*, defaults to `True`): Whether to apply layer normalization to the feature maps in case the model is used as backbone. reshape_hidden_states (`bool`, *optional*, defaults to `True`): Whether to reshape the feature maps to 4D tensors of shape `(batch_size, hidden_size, height, width)` in case the model is used as backbone. If `False`, the feature maps will be 3D tensors of shape `(batch_size, seq_len, hidden_size)`. Example: ```python >>> from transformers import PixioConfig, PixioModel >>> # Initializing a Pixio pixio-huge style configuration >>> configuration = PixioConfig() >>> # Initializing a model (with random weights) from the pixio-huge style configuration >>> model = PixioModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```pixioc t|di|||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ | |_ ||_||_dgt!d|dzDcgc]}d| c}z|_|j%||||_||_||_ycc}w)Nstemstage) out_indices out_features)super__init__ hidden_sizenum_hidden_layersnum_attention_heads mlp_ratio hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps image_size patch_size num_channelsqkv_biasdrop_path_raterange stage_names"set_output_features_output_indicesapply_layernormreshape_hidden_states n_cls_tokens)selfrrrrr$rrrrrrrrrrr r r"r#kwargsidx __class__s _/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/pixio/configuration_pixio.pyrzPixioConfig.__init__es. "6"&!2#6 "$#6 ,H)!2,$$(  ,"8aIZ]^I^@_&`se}&`` //KVb/c.%:"( 'as C)i gelur/g{Gz?gư>r+rTr/NNTT)__name__ __module__ __qualname____doc__ model_typer __classcell__)r(s@r)rrsVG RJ%("),),)rN)backbone_utilsrconfiguration_utilsrr__all__rr7r)r;s)*23x)%'7x)v /r7