ktolnos/helpsteer3_goldSkywork-Reward-V2-Llama-3.1-8B
收藏Hugging Face2025-10-22 更新2025-10-25 收录
下载链接:
https://hf-mirror.com/datasets/ktolnos/helpsteer3_goldSkywork-Reward-V2-Llama-3.1-8B
下载链接
链接失效反馈官方服务:
资源简介:
该数据集包含了用户在特定场景下的选择偏好以及相关的奖励信息,具体包括用户偏好的强度、选择和拒绝的内容及角色、奖励值以及是否与黄金标准一致等字段。数据集分为训练集和测试集,可用于模型训练和评估。
The dataset contains user preference strengths, chosen and rejected content and roles, reward values, and whether they agree with the gold standard, split into training and test sets for model training and evaluation.
提供机构:
ktolnos



