ticoAg/hh_rlhf_helpful_cn_test
收藏资源简介:
# Note > some rm data from public dataset - format ```json { "history": [ ["query1", "answer1"], ["query2", "answer2"] ], "prompt": "query", "input": "input for query", "output": [ "output rank1", "output rank2", "output rank3" ] } ``` Thanks - [beyond/rlhf-reward-single-round-trans_chinese](https://huggingface.co/datasets/beyond/rlhf-reward-single-round-trans_chinese) : - [dikw/hh_rlhf_cn](https://huggingface.co/datasets/dikw/hh_rlhf_cn) - [liyucheng/zhihu_rlhf_3k](https://huggingface.co/datasets/liyucheng/zhihu_rlhf_3k)
# 备注 > 本数据集包含部分取自公开数据集的奖励模型(Reward Model,RM)数据 - 数据格式 json { "history": [ ["查询1", "回复1"], ["查询2", "回复2"] ], "prompt": "查询", "input": "用于生成查询的输入内容", "output": [ "排序第一的输出结果", "排序第二的输出结果", "排序第三的输出结果" ] } 感谢以下公开数据集来源: - [beyond/rlhf-reward-single-round-trans_chinese](https://huggingface.co/datasets/beyond/rlhf-reward-single-round-trans_chinese) - [dikw/hh_rlhf_cn](https://huggingface.co/datasets/dikw/hh_rlhf_cn) - [liyucheng/zhihu_rlhf_3k](https://huggingface.co/datasets/liyucheng/zhihu_rlhf_3k)
数据集详情
数据格式
数据集采用JSON格式,具体结构如下:
json { "history": [ ["query1", "answer1"], "query2", "answer2" ], "prompt": "query", "input": "input for query", "output": [ "output rank1", "output rank2", "output rank3" ] }



