cchoi1/humaneval_qwen32b_sol_best_of_200_grpo
收藏Hugging Face2025-03-28 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/cchoi1/humaneval_qwen32b_sol_best_of_200_grpo
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含三个字段：prompt（提示文本）、completion（完成文本）和reward（奖励值）。数据集被划分为训练集，共包含32800个示例。数据集的总大小为22295945字节，下载大小为1614622字节。
The dataset includes three fields: prompt (prompt text), completion (completed text), and reward (reward value). The dataset is split into a training set, containing a total of 32,800 examples. The total size of the dataset is 22,295,945 bytes, with a download size of 1,614,622 bytes.
提供机构：
cchoi1
