clembench-playpen/DPO_turn_allneg_old_and_new_klimit
收藏Hugging Face2025-05-07 更新2025-07-05 收录
下载链接:
https://hf-mirror.com/datasets/clembench-playpen/DPO_turn_allneg_old_and_new_klimit
下载链接
链接失效反馈官方服务:
资源简介:
该数据集包含了一系列游戏回合的相关信息,其中包括游戏ID、版本、实验类型、回合编号、模型成功与否的标记、提示信息、玩家信息、分支回合编号,以及玩家在每个回合中的选择和拒绝的行动。数据集提供了训练集的分割,并包含了相关文件的路径配置。具体的应用场景和数据集目的未在README中说明。
The dataset consists of a series of game rounds with related information including game ID, version, experiment type, round number, model success/failure markers, prompt information, player information, branch round number, and the players choices and rejections in each round. The dataset provides a training set split and includes path configurations for the relevant files. The specific application scenario and purpose of the dataset are not described in the README.
提供机构:
clembench-playpen



