cskokgibbs/BEELINE-HepG2-no-GTL-pretokenized-NT

该数据集包含基因(gene)、转录因子(TF)、交互作用(interaction)、格式化输入(formatted_inputs)、输入ID(input_ids)、注意力掩码(attention_mask)和标签(labels)等字段。数据集被划分为训练集，其中包含5185845个示例，大小为28913247909字节。提供的配置信息中包含了训练集的数据文件路径。The dataset includes fields such as gene, TF, interaction, formatted_inputs, input_ids, attention_mask, and labels. The dataset is split into a training set, which contains 5185845 examples and is 28913247909 bytes in size. The configuration information provided includes the file path for the training set data.