^jjjdZddlmZddlmZddlmZedeGdd eZd gZy ) zPerceiver model configuration)strict)PreTrainedConfig)auto_docstringzdeepmind/language-perceiver) checkpointceZdZUdZdZdZeed<dZeed<dZ eed<d Z eed <d Z eed <d Z eed<d Z eed<dZedzed<dZedzed<dZeed<d Zeed<d Zeed<dZeed<dZeezed<dZeed<dZeed<dZeed <d!Zeed"<d#Zeed$<d%Zeeezeeefzed&<d'Z eeeed(fzed)<d*Z!eed+<d,Z"eed-<d*Z#eed.<d/Z$eeeed(fzed0<d1Z%eed2<d3Z&eed4<y)5PerceiverConfiga num_latents (`int`, *optional*, defaults to 256): The number of latents. d_latents (`int`, *optional*, defaults to 1280): Dimension of the latent embeddings. num_blocks (`int`, *optional*, defaults to 1): Number of blocks in the Transformer encoder. num_self_attends_per_block (`int`, *optional*, defaults to 26): The number of self-attention layers per block. num_self_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each self-attention layer in the Transformer encoder. num_cross_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each cross-attention layer in the Transformer encoder. qk_channels (`int`, *optional*): Dimension to project the queries + keys before applying attention in the cross-attention and self-attention layers of the encoder. Will default to preserving the dimension of the queries if not specified. v_channels (`int`, *optional*): Dimension to project the values before applying attention in the cross-attention and self-attention layers of the encoder. Will default to preserving the dimension of the queries if not specified. cross_attention_shape_for_attention (`str`, *optional*, defaults to `"kv"`): Dimension to use when downsampling the queries and keys in the cross-attention layer of the encoder. self_attention_widening_factor (`int`, *optional*, defaults to 1): Dimension of the feed-forward layer in the cross-attention layer of the Transformer encoder. cross_attention_widening_factor (`int`, *optional*, defaults to 1): Dimension of the feed-forward layer in the self-attention layers of the Transformer encoder. use_query_residual (`float`, *optional*, defaults to `True`): Whether to add a query residual in the cross-attention layer of the encoder. image_size (`int`, *optional*, defaults to 56): Size of the images after preprocessing, for [`PerceiverForImageClassificationLearned`]. train_size (`list[int]`, *optional*, defaults to `[368, 496]`): Training size of the images for the optical flow model. num_frames (`int`, *optional*, defaults to 16): Number of video frames used for the multimodal autoencoding model. audio_samples_per_frame (`int`, *optional*, defaults to 1920): Number of audio samples per frame for the multimodal autoencoding model. samples_per_patch (`int`, *optional*, defaults to 16): Number of audio samples per patch when preprocessing the audio for the multimodal autoencoding model. output_shape (`list[int]`, *optional*, defaults to `[1, 16, 224, 224]`): Shape of the output (batch_size, num_frames, height, width) for the video decoder queries of the multimodal autoencoding model. This excludes the channel dimension. output_num_channels (`int`, *optional*, defaults to 512): Number of output channels for each modalitiy decoder. Example: ```python >>> from transformers import PerceiverModel, PerceiverConfig >>> # Initializing a Perceiver deepmind/language-perceiver style configuration >>> configuration = PerceiverConfig() >>> # Initializing a model from the deepmind/language-perceiver style configuration >>> model = PerceiverModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` perceiver num_latentsi d_latentsid_model num_blocksnum_self_attends_per_blocknum_self_attention_headsnum_cross_attention_headsN qk_channels v_channelskv#cross_attention_shape_for_attentionself_attention_widening_factorcross_attention_widening_factorgelu hidden_actg?attention_probs_dropout_probg{Gz?initializer_rangeg-q=layer_norm_epsTuse_query_residuali vocab_sizeimax_position_embeddings8 image_size)ipi. train_size num_framesiaudio_samples_per_framesamples_per_patch)rr'r+ output_shapeioutput_num_channelsi_label_trainable_num_channels)'__name__ __module__ __qualname____doc__ model_typer int__annotations__r rrrrrrrrstrrrrrfloatrr r!boolr"r#r%listtupler&r(r)r*r,r-r./var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/perceiver/configuration_perceiver.pyr r sn8 tJKIsGSJ&(($%c%%&s&"Kt"!Jd !/3'3*+"C++,#S,J03 %#+3#u#!NE!##J#'S'46Jd3i%S/16.8JS E#s(O+8J#'S's0AL$s)eCHo-A"")-!3-r<r N) r2huggingface_hub.dataclassesrconfiguration_utilsrutilsrr __all__r;r<r=rBsK$.3#89W.&W.:W.t  r<