IgAdZddlZddlmZddlmZmZmZmZm Z m Z er ddl m Z ddl mZddlmZdd lmZdd l mZej(eZGd d eZGd deZGddeZGddeZy)zOWL-ViT model configurationN OrderedDict) TYPE_CHECKINGAnyDictMappingOptionalUnion)ProcessorMixin) TensorType)PretrainedConfig) OnnxConfig)loggingc|eZdZdZdZ dfd Zedeee jfddfdZ xZ S) OwlViTTextConfiga This is the configuration class to store the configuration of an [`OwlViTTextModel`]. It is used to instantiate an OwlViT 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 OwlViT [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32) 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 OWL-ViT text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`OwlViTTextModel`]. hidden_size (`int`, *optional*, defaults to 512): 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 8): Number of attention heads for each attention layer in the Transformer encoder. max_position_embeddings (`int`, *optional*, defaults to 16): 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). hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): 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. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`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. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). pad_token_id (`int`, *optional*, defaults to 0): The id of the padding token in the input sequences. bos_token_id (`int`, *optional*, defaults to 49406): The id of the beginning-of-sequence token in the input sequences. eos_token_id (`int`, *optional*, defaults to 49407): The id of the end-of-sequence token in the input sequences. Example: ```python >>> from transformers import OwlViTTextConfig, OwlViTTextModel >>> # Initializing a OwlViTTextModel with google/owlvit-base-patch32 style configuration >>> configuration = OwlViTTextConfig() >>> # Initializing a OwlViTTextConfig from the google/owlvit-base-patch32 style configuration >>> model = OwlViTTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```owlvit_text_modelc t|d| | |d|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ y)N) pad_token_id bos_token_id eos_token_id) super__init__ vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsmax_position_embeddings hidden_actlayer_norm_epsattention_dropoutinitializer_rangeinitializer_factor)selfrrrrrr r!r"r#r$r%rrrkwargs __class__s l/var/www/html/answerous/venv/lib/python3.12/site-packages/transformers/models/owlvit/configuration_owlvit.pyrzOwlViTTextConfig.__init__`sv$ sl\hslrs$&!2!2#6 '>$$,!2!2"4pretrained_model_name_or_pathreturnrc >|j||j|fi|\}}|jddk(r|d}d|vrGt|dr;|d|jk7r)t j d|dd|jd|j|fi|S)N model_typeowlvit text_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors._set_token_in_kwargsget_config_dictgethasattrr.loggerwarning from_dictclsr+r' config_dicts r)from_pretrainedz OwlViTTextConfig.from_pretraineds   (1c112OZSYZ V ??< (H 4%m4K ; &73 +E+VbJcgjguguJu NN0\1J0KKk>>""pr  s}}[3F33r*)ii  quick_geluh㈵>{Gz??rii __name__ __module__ __qualname____doc__r.r classmethodr strosPathLiker? __classcell__r(s@r)rr"ss9 v%J "5@4E#r{{BR