TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval__3args_basemodel_LLMSCORED
收藏Hugging Face2025-11-04 更新2025-11-15 收录
下载链接：
https://hf-mirror.com/datasets/TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval__3args_basemodel_LLMSCORED
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含问题、答案以及与任务相关的配置和来源信息。数据集还包含了提示、模型响应及其评估信息，以及其他一些元数据字段，如难度、领域、评估类型等。数据集分为训练集，其大小为195881603字节，共有11481个示例。
The dataset includes questions, answers, and task-related configurations and sources. It also contains prompts, model responses and their evaluation information, as well as other metadata fields such as difficulty, domain, evaluation type, etc. The dataset is split into a training set, which is 195881603 bytes in size and contains 11481 examples.
提供机构：
TAUR-dev
