cskokgibbs/BEELINE-human-v2-pretokenized-NT
收藏官方服务：
资源简介：
这是一个包含基因、转录因子、交互信息以及其他用于模型训练的特征（如输入ID、注意力掩码和标签）的数据集。数据集仅包含一个训练集部分，拥有大约16950257个示例，文件大小为约122723131290字节。数据集可以通过默认配置文件中指定的路径进行访问。
This dataset includes features such as gene, TF (transcription factor), interaction, and other features for model training like input IDs, attention masks, and labels. The dataset contains only a training split with approximately 16,950,257 examples and a file size of about 122,723,131,290 bytes. The dataset can be accessed via the paths specified in the default configuration file.
提供机构：
cskokgibbs
