o Zh.:@sbdZddlmZddlmZeeZGdddeZGdddeZ Gdd d eZ gd Z d S) zBlip model configuration)PretrainedConfig)loggingcsReZdZdZdZdZ              dfdd ZZS)BlipTextConfiga This is the configuration class to store the configuration of a [`BlipTextModel`]. It is used to instantiate a BLIP text 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 `BlipText` used by the [base architectures](https://huggingface.co/Salesforce/blip-vqa-base). 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 30524): Vocabulary size of the `Blip` text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`BlipModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. encoder_hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers from the vision model. intermediate_size (`int`, *optional*, defaults to 3072): 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 512): 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 `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. 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. bos_token_id (`int`, *optional*, defaults to 30522): The id of the `beginning-of-sequence` token. eos_token_id (`int`, *optional*, defaults to 2): The id of the `end-of-sequence` token. pad_token_id (`int`, *optional*, defaults to 0): The id of the `padding` token. sep_token_id (`int`, *optional*, defaults to 102): The id of the `separator` token. is_decoder (`bool`, *optional*, defaults to `True`): Whether the model is used as a decoder. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). label_smoothing (float, *optional*): A float in [0.0, 1.0]. Specifies the amount of smoothing when computing the loss, where 0.0 means no smoothing. The targets become a mixture of the original ground truth and a uniform distribution as described in `Rethinking the Inception Architecture for Computer Vision `__. Default: :math:`0.0`. Example: ```python >>> from transformers import BlipTextConfig, BlipTextModel >>> # Initializing a BlipTextConfig with Salesforce/blip-vqa-base style configuration >>> configuration = BlipTextConfig() >>> # Initializing a BlipTextModel (with random weights) from the Salesforce/blip-vqa-base style configuration >>> model = BlipTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zblip_text_model text_config