qiP)>dZddlmZddlmZGddeeZdgZy)zBEiT model configuration)BackboneConfigMixin)PreTrainedConfigcjeZdZdZdZddddddddd d d d d dddddddgdddddddddddffd ZxZS) BeitConfiga This is the configuration class to store the configuration of a [`BeitModel`]. It is used to instantiate an BEiT 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 BEiT [microsoft/beit-base-patch16-224-pt22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k) architecture. Args: vocab_size (`int`, *optional*, defaults to 8192): Vocabulary size of the BEiT model. Defines the number of different image tokens that can be used during pre-training. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer 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-12): The epsilon used by the layer normalization layers. image_size (`int`, *optional*, defaults to 224): 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. use_mask_token (`bool`, *optional*, defaults to `False`): Whether to use a mask token for masked image modeling. use_absolute_position_embeddings (`bool`, *optional*, defaults to `False`): Whether to use BERT-style absolute position embeddings. use_relative_position_bias (`bool`, *optional*, defaults to `False`): Whether to use T5-style relative position embeddings in the self-attention layers. use_shared_relative_position_bias (`bool`, *optional*, defaults to `False`): Whether to use the same relative position embeddings across all self-attention layers of the Transformer. layer_scale_init_value (`float`, *optional*, defaults to 0.1): Scale to use in the self-attention layers. 0.1 for base, 1e-5 for large. Set 0 to disable layer scale. drop_path_rate (`float`, *optional*, defaults to 0.1): Stochastic depth rate per sample (when applied in the main path of residual layers). use_mean_pooling (`bool`, *optional*, defaults to `True`): Whether to mean pool the final hidden states of the patches instead of using the final hidden state of the CLS token, before applying the classification head. pool_scales (`tuple[int]`, *optional*, defaults to `[1, 2, 3, 6]`): Pooling scales used in Pooling Pyramid Module applied on the last feature map. use_auxiliary_head (`bool`, *optional*, defaults to `True`): Whether to use an auxiliary head during training. auxiliary_loss_weight (`float`, *optional*, defaults to 0.4): Weight of the cross-entropy loss of the auxiliary head. auxiliary_channels (`int`, *optional*, defaults to 256): Number of channels to use in the auxiliary head. auxiliary_num_convs (`int`, *optional*, defaults to 1): Number of convolutional layers to use in the auxiliary head. auxiliary_concat_input (`bool`, *optional*, defaults to `False`): Whether to concatenate the output of the auxiliary head with the input before the classification layer. semantic_loss_ignore_index (`int`, *optional*, defaults to 255): The index that is ignored by the loss function of the semantic segmentation model. 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. add_fpn (`bool`, *optional*, defaults to `False`): Whether to add a FPN as part of the backbone. Only relevant for [`BeitBackbone`]. 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)`. Only relevant for [`BeitBackbone`]. Example: ```python >>> from transformers import BeitConfig, BeitModel >>> # Initializing a BEiT beit-base-patch16-224-pt22k style configuration >>> configuration = BeitConfig() >>> # Initializing a model (with random weights) from the beit-base-patch16-224-pt22k style configuration >>> model = BeitModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```beiti i i gelugg{Gz?g-q=rFg?T)rg?r Nc  ~d| vr|| jd}t"|di| ||_||_||_||_||_||_||_ ||_ | |_ | |_ | |_ | |_| |_||_||_||_||_||_||_||_||_||_||_||_||_||_||_dgt=d|j dzD!cgc]}!d|! c}!z|_|jA||||_!||_"ycc}!w)Nsegmentation_indicesstemr stage) out_indices out_features)#popsuper__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps image_size patch_size num_channelsuse_mask_token use_absolute_position_embeddingsuse_relative_position_bias!use_shared_relative_position_biaslayer_scale_init_valuedrop_path_rateuse_mean_pooling pool_scalesuse_auxiliary_headauxiliary_loss_weightauxiliary_channelsauxiliary_num_convsauxiliary_concat_inputsemantic_loss_ignore_indexrange stage_names"set_output_features_output_indicesadd_fpnreshape_hidden_states)#selfrrrrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4r5rrr9r:kwargsidx __class__s# ]/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/beit/configuration_beit.pyrzBeitConfig.__init__wsdF "V + 0C **%;s@r?rrs}^ @J%().#(*/" !$#&"AJ;J;rN)rCbackbone_utilsrconfiguration_utilsrr__all__rrFr?rJs,13m;$&6m;` .rF