RUC-AIBOX/STILL-3-RL-90K

该数据集包含数据源、提示信息（内容与角色）、能力、奖励模型（地面真实与风格）以及额外信息（索引与数据集划分）。数据集分为训练集，其中包含大约88054个示例，大小为约129MB。提供了默认配置，用于指定训练集数据文件的路径。The dataset includes data source, prompt information (content and role), ability, reward model (ground truth and style), and extra information (index and split). The dataset is split into a training set, which contains about 88054 examples and is approximately 129MB in size. A default configuration is provided to specify the path to the training set data files.