g"^dZddlmZddlmZejeZGddeZdS)zBioGPT model configuration)PretrainedConfig)loggingcLeZdZdZdZ dfd ZxZS) BioGptConfiga This is the configuration class to store the configuration of a [`BioGptModel`]. It is used to instantiate an BioGPT 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 BioGPT [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) 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 42384): Vocabulary size of the BioGPT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`BioGptModel`]. hidden_size (`int`, *optional*, defaults to 1024): Dimension of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 4096): Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. 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"` 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 1024): 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 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. scale_embedding (`bool`, *optional*, defaults to `True`): Scale embeddings by diving by sqrt(d_model). 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`. layerdrop (`float`, *optional*, defaults to 0.0): Please refer to the paper about LayerDrop: https://arxiv.org/abs/1909.11556 for further details activation_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for activations inside the fully connected layer. pad_token_id (`int`, *optional*, defaults to 1): Padding token id. bos_token_id (`int`, *optional*, defaults to 0): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 2): End of stream token id. Example: ```python >>> from transformers import BioGptModel, BioGptConfig >>> # Initializing a BioGPT microsoft/biogpt style configuration >>> configuration = BioGptConfig() >>> # Initializing a model from the microsoft/biogpt style configuration >>> model = BioGptModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```biogpt鐥gelu皙?{Gz?-q=Tc ||_| |_||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ ||_ ||_tjd|||d|dS)N) pad_token_id bos_token_id eos_token_id) vocab_sizemax_position_embeddings hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_epsscale_embedding use_cache layerdropactivation_dropoutsuper__init__)selfrrrrrr r!r"rr#r$r%r&r'r(rrrkwargs __class__s k/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/biogpt/configuration_biogpt.pyr*zBioGptConfig.__init__^s,%'>$&!2#6 !2$#6 ,H)!2,."""4sl\hsslrsssss)rr r r r r rrr rrTTrrrrr)__name__ __module__ __qualname____doc__ model_typer* __classcell__)r-s@r.rrsA A FJ%( $'%t%t%t%t%t%t%t%t%t%tr/rN) r3configuration_utilsrutilsr get_loggerr0loggerrrr/r.r:s! 333333  H % %ktktktktkt#ktktktktktr/