Species-aware DNA language modeling - data

Data accompanying the publication Species-aware DNA language modeling. For code, see: https://github.com/DennisGankin/species-aware-DNA-LM (for the latest version) or the code.zip file. The data directory contains model checkpoints, baselines models, evaluation results and datasets used for training, testing and downstream tasks. It has the following structure: data/ Datasets and subdirectories - data/results/ Results from different test runs - data/models/ Model checkpoints - data/baselines/ Baseline models本数据集配套于《物种感知型DNA语言建模》（Species-aware DNA language modeling）学术论文。相关代码可通过以下途径获取：最新版本请访问 https://github.com/DennisGankin/species-aware-DNA-LM，亦可通过code.zip文件获取。数据目录包含用于训练、测试及下游任务的模型检查点、基线模型、评估结果与训练数据集，其目录结构如下： data/：数据集与子目录 - data/results/：不同测试运行的结果 - data/models/：模型检查点 - data/baselines/：基线模型