TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_AT_STAR-SFT-countdown_3arg-eval_sft
收藏数据链接：
官方服务：
资源简介：
该数据集包含了问题、答案和相关提示信息，用于模型训练和评估。数据集还包括了模型响应和相关评估指标，如正确率、技能计数和总响应数等。数据集分为测试集，共有1000个示例。
The dataset includes questions, answers, and related prompt information for model training and evaluation. It also contains model responses and related evaluation metrics such as accuracy, skill count, and total number of responses. The dataset is split into a test set with a total of 1000 examples.
提供机构：
TAUR-dev
