zjhhhh/game_stage1_zjhhhh__qwen2.5_3B_Instruct_min_stage1_seed_555134_eta_1e4_step_301
收藏数据链接:
官方服务:
资源简介:
该数据集包含了提示、要求以及多个基础和模型响应的字符串字段,还有评委对每个响应的多数和平均评分。数据集分为训练集,共有200个示例。
The dataset includes prompt, requirements, and multiple base and model responses as string fields, along with the majority and average ratings from judges for each response. The dataset is split into a training set with a total of 200 examples.
提供机构:
zjhhhh


