o ei4@s@dZddlmZddlmZeeZGdddeZdgZ dS)zRoBERTa configuration)PreTrainedConfig)loggingcsNeZdZdZdZ              dfdd ZZS) RobertaConfiga This is the configuration class to store the configuration of a [`RobertaModel`]. It is used to instantiate a RoBERTa 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 RoBERTa [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) 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 50265): Vocabulary size of the RoBERTa model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`RobertaModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. 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). type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`RobertaModel`]. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. is_decoder (`bool`, *optional*, defaults to `False`): Whether the model is used as a decoder or not. If `False`, the model is used as an encoder. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. classifier_dropout (`float`, *optional*): The dropout ratio for the classification head. Examples: ```python >>> from transformers import RobertaConfig, RobertaModel >>> # Initializing a RoBERTa configuration >>> configuration = RobertaConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = RobertaModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```robertaY gelu皙?{Gz?-q=TNFc stjdi|| |_||_||_||_||_||_||_||_ ||_ ||_ ||_ ||_ ||_||_| |_| |_| |_| |_||_||_dS)N)super__init__ pad_token_id bos_token_id eos_token_idtie_word_embeddings is_decoderadd_cross_attention vocab_size hidden_sizenum_hidden_layersnum_attention_heads hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_eps use_cacheclassifier_dropout)selfrrrrr rr!r"r#r$r%r&rrrr'r(rrrkwargs __class__ro/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/roberta/configuration_roberta.pyrXs* zRobertaConfig.__init__)rrrrr r r r r r rrrrr TNFFT)__name__ __module__ __qualname____doc__ model_typer __classcell__rrr+r-rs0=rN) r1configuration_utilsrutilsr get_loggerr.loggerr__all__rrrr-s     p