Ayush-Singh/reward-bench-CodeRM-8B-normal
收藏Hugging Face2025-02-08 更新2025-02-15 收录
下载链接:
https://hf-mirror.com/datasets/Ayush-Singh/reward-bench-CodeRM-8B-normal
下载链接
链接失效反馈官方服务:
资源简介:
该数据集包含了编程语言相关的提示(prompt)、选择(chosen)、选择模型(chosen_model)、拒绝(rejected)、拒绝模型(rejected_model)、子集(subset)、唯一标识符(id)以及选择和拒绝的奖励(reward_chosen, reward_rejected)。数据集被划分为六个子集,每个子集包含了164个示例,分别对应不同的编程语言。
The dataset includes programming language-related prompts, choices, chosen models, rejections, rejected models, subsets, unique identifiers, and rewards for choices and rejections. The dataset is divided into six subsets, each containing 164 examples, corresponding to different programming languages.
提供机构:
Ayush-Singh



