qi4ddlmZddlmZejeZGddeZGddeZGddeZ gd Z y ) )PreTrainedConfig)loggingceZdZdZdZdZ ddededededed ed ed ed ed edede dededeffd Z xZ S)Aimv2VisionConfiga This is the configuration class to store the configuration of a [`Aimv2VisionModel`]. It is used to instantiate a AIMv2 vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the vision encoder of the AIMv2 [apple/aimv2-large-patch14-224](https://huggingface.co/apple/aimv2-large-patch14-224) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 1024): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 2816): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer encoder. num_channels (`int`, *optional*, defaults to 3): Number of channels in the input images. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 14): The size (resolution) of each patch. rms_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the rms normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. qkv_bias (`bool`, *optional*, defaults to `False`): Whether to add a bias to the queries, keys and values. mlp_bias (`bool`, *optional*, defaults to `False`): Whether to add a bias to the Linear layers or Not. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the for initializing all weight matrices. use_head (`str`, *optional*, defaults to `True`): Whether to use Attention Pooling Head or Not. is_native (`str`, *optional*, defaults to `False`): Whether to use ckpt trained for image native resolution or not. Example: ```python >>> from transformers import SiglipVisionConfig, SiglipVisionModel >>> # Initializing a Aimv2VisionConfig with apple/aimv2-large-patch14-224 style configuration >>> configuration = Aimv2VisionConfig() >>> # Initializing a Aimv2VisionModel (with random weights) from the apple/aimv2-large-patch14-224 style configuration >>> model = Aimv2VisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```aimv2_vision_model vision_config hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads num_channels image_size patch_size rms_norm_epsattention_dropoutqkv_biasmlp_bias hidden_actinitializer_rangeuse_head is_nativec t|di|||_||_||_||_||_||_||_| |_ | |_ ||_ | |_ | |_ | |_||_||_yN)super__init__r r r r r rrrrrrrrrr)selfr r r r r rrrrrrrrrrkwargs __class__s _/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/aimv2/configuration_aimv2.pyrzAimv2VisionConfig.__init__Xs& "6"&!2!2#6 ($$!2$  !2    (")ii rh㈵>FFsilu{Gz?TF __name__ __module__ __qualname____doc__ model_typebase_config_keyintfloatboolstrr __classcell__rs@r rrs6 p&J%O !%!##$"#& #'!$#$#$# $# ! $#  $#$#$#$#!$#$#$#$#!$#$# !$#$#r!rc|eZdZdZdZdZ ddededededed ed ed ed ed e dededeffd Z xZ S)Aimv2TextConfiga This is the configuration class to store the configuration of a [`Aimv2TextModel`]. It is used to instantiate a AIMv2 text encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the text encoder of the AIMv2 [apple/aimv2-large-patch14-224-lit](https://huggingface.co/apple/aimv2-large-patch14-224-lit) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 49408): Vocabulary size of the AIMv2 text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Aimv2Model`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 2048): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 6): Number of attention heads for each attention layer in the Transformer encoder. rms_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the rms normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. qkv_bias (`bool`, *optional*, defaults to `False`): Whether to add a bias to the queries, keys and values. mlp_bias (`bool`, *optional*, defaults to `False`): Whether to add a bias to the Linear layers or Not. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. eos_token_id (`int`, *optional*, defaults to 49407): The id of the end-of-sequence token in the vocabulary. max_position_embeddings (`int`, *optional*, defaults to 77): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the for initializing all weight matrices. aimv2_text_model text_config vocab_sizer r r r rrrrr eos_token_idmax_position_embeddingsrc t|di|| |_||_||_||_||_||_| |_| |_ ||_ | |_ | |_ ||_ ||_yr)rrr<r;r r r r r=rrrrrr)rr;r r r r rrrrrr<r=rrrs r rzAimv2TextConfig.__init__sy" "6"($&!2!2#6 '>$$!2!2    (r!) iii r&r'FFr(iMr)r*r6s@r r8r8s'R$J#O !%!##$"#& !')"& ) ) ) )  ) ! ) )! ) ) ) ) )"% )  ) )r!r8c4eZdZdZdZeedZ dfd ZxZ S) Aimv2Configa@ [`Aimv2Config`] is the configuration class to store the configuration of a [`Aimv2Model`]. It is used to instantiate a AIMv2 model according to the specified arguments, defining the text model and vision model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the AIMv2 [apple/aimv2-large-patch14-224-lit](https://huggingface.co/apple/aimv2-large-patch14-224-lit) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Aimv2TextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Aimv2VisionConfig`]. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and vision projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The initial value of the *logit_scale* parameter. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import Aimv2Config, Aimv2Model >>> # Initializing a Aimv2Config with apple/aimv2-large-patch14-224-lit style configuration >>> configuration = Aimv2Config() >>> # Initializing a Aimv2Model (with random weights) from the apple/aimv2-large-patch14-224-lit style configuration >>> model = Aimv2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a Aimv2Config from a Aimv2TextConfig and a Aimv2VisionConfig >>> from transformers import Aimv2TextConfig, Aimv2VisionConfig >>> # Initializing a AIMv2Text and AIMv2Vision configuration >>> config_text = Aimv2TextConfig() >>> config_vision = Aimv2VisionConfig() >>> config = Aimv2Config(text_config=config_text, vision_config=config_vision) ```aimv2)r:rc ^||_||_d|_| t}tj dnt |tr tdi|}| t}tj dnt |tr tdi|}||_ ||_ t|0di|y)NgY@zP`text_config` is `None`. Initializing the `Aimv2TextConfig` with default values.zT`vision_config` is `None`. initializing the `Aimv2VisionConfig` with default values.r) projection_dimlogit_scale_init_valuemax_logit_scaler8loggerinfo isinstancedictrr:rrr)rr:rrFrGrrs r rzAimv2Config.__init__s-&<#$  )+K KKj k  T *)8K8K  -/M KKn o  t ,-> >M&* "6"r!)NNig/L F@) r+r,r-r.r/r8r sub_configsrr5r6s@r rCrCs,+ ZJ"1DUVK`f##r!rC)rCrr8N) configuration_utilsrutilsr get_loggerr+rIrr8rC__all__rr!r rRsY*4   H %`#(`#FM)&M)`F#"F#R Br!