# Copyright 2022 The HuggingFace Team and Microsoft Research AI4Science All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. """BioGPT model configuration""" from huggingface_hub.dataclasses import strict from ...configuration_utils import PreTrainedConfig from ...utils import auto_docstring @auto_docstring(checkpoint="microsoft/biogpt") @strict class BioGptConfig(PreTrainedConfig): r""" 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 ```""" model_type = "biogpt" vocab_size: int = 42384 hidden_size: int = 1024 num_hidden_layers: int = 24 num_attention_heads: int = 16 intermediate_size: int = 4096 hidden_act: str = "gelu" hidden_dropout_prob: float | int = 0.1 attention_probs_dropout_prob: float | int = 0.1 max_position_embeddings: int = 1024 initializer_range: float = 0.02 layer_norm_eps: float = 1e-12 scale_embedding: bool = True use_cache: bool = True layerdrop: float | int = 0.0 activation_dropout: float | int = 0.0 pad_token_id: int | None = 1 bos_token_id: int | None = 0 eos_token_id: int | list[int] | None = 2 tie_word_embeddings: bool = True __all__ = ["BioGptConfig"]