a ½ Àh¬5ã@sjddlmZddlmZddlmZe e¡ZGdd„deƒZ Gdd„deƒZ Gd d „d eƒZ gd ¢Z d S) é)ÚOptionalé)ÚPretrainedConfig)ÚloggingcsLeZdZdZdZdZdeeeeeeeeeeee eeedœ‡fdd„ Z ‡Z S)ÚAimv2VisionConfiga“ 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 ```Zaimv2_vision_modelÚ vision_configéé ééréàéçñh㈵øä>çFÚsiluç{®Gáz”?T)Ú hidden_sizeÚintermediate_sizeÚnum_hidden_layersÚnum_attention_headsÚ num_channelsÚ image_sizeÚ patch_sizeÚ rms_norm_epsÚattention_dropoutÚqkv_biasÚmlp_biasÚ hidden_actÚinitializer_rangeÚuse_headÚ is_nativec sptƒjfi|¤Ž||_||_||_||_||_||_||_| |_ | |_ ||_ | |_ | |_ | |_||_||_dS)N)ÚsuperÚ__init__rrrrrrrrrrrrrrr )Úselfrrrrrrrrrrrrrrr Úkwargs©Ú __class__©úi/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/aimv2/configuration_aimv2.pyr"[s zAimv2VisionConfig.__init__)rr r r rr r rrFFrrTF) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚbase_config_keyÚintÚfloatÚboolÚstrr"Ú __classcell__r'r'r%r(rsF8ððrcsTeZdZdZdZdZdeeeeeeeeee e ee eeeedœ‡fdd„ Z ‡Z S)ÚAimv2TextConfigaÄ 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. pad_token_id (`int`, *optional*, defaults to 1): The id of the padding token in the vocabulary. bos_token_id (`int`, *optional*, defaults to 49406): The id of the beginning-of-sequence token in the vocabulary. 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. Zaimv2_text_modelÚ text_configéÁééé érrFrNéÿÀéMr)Ú vocab_sizerrrrrrrrrÚ pad_token_idÚ bos_token_idÚ eos_token_idÚmax_position_embeddingsrc sftƒjf| | | dœ|¤Ž||_||_||_||_||_||_| |_||_ ||_ | |_ ||_ ||_ dS)N)r>r?r@)r!r"r=rrrrrArrrrrr)r#r=rrrrrrrrrr>r?r@rArr$r%r'r(r"³szAimv2TextConfig.__init__)r6r7r8r9r:rrFFrNNr;r<r) r)r*r+r,r-r.r/r0r1r2rr"r3r'r'r%r(r4‚sF-ððr4cs0eZdZdZdZeedœZd ‡fdd„ Z‡Z S) Ú 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) ```Zaimv2)r5rNéçƒ/L¦ F@c sttƒjfi|¤Ž|dur(i}t d¡|dur>i}t d¡tfi|¤Ž|_tfi|¤Ž|_||_||_ d|_ dS)NzP`text_config` is `None`. Initializing the `Aimv2TextConfig` with default values.zT`vision_config` is `None`. initializing the `Aimv2VisionConfig` with default values.gY@) r!r"ÚloggerÚinfor4r5rrÚprojection_dimÚlogit_scale_init_valueZmax_logit_scale)r#r5rrGrHr$r%r'r(r"s  zAimv2Config.__init__)NNrCrD) r)r*r+r,r-r4rZ sub_configsr"r3r'r'r%r(rB×s - ÿrB)rBrr4N) ÚtypingrZconfiguration_utilsrÚutilsrZ get_loggerr)rErr4rBÚ__all__r'r'r'r(Ús    cUE