cchoi1/humaneval_qwen7b_sol_best_of_200_grpo
收藏Hugging Face2025-03-30 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/cchoi1/humaneval_qwen7b_sol_best_of_200_grpo
下载链接
链接失效反馈官方服务：
资源简介：
这是一个包含提示(prompt)、完成(completion)和奖励(reward)字段的数据集，其中prompt和completion为字符串类型，reward为浮点数类型。数据集分为训练集(train)，共有32800个示例，总文件大小为22676763字节。提供的配置信息中包含了训练集的数据文件路径。
This dataset includes fields for prompt, completion, and reward, with prompt and completion being string types and reward being a float type. The dataset is split into a training set (train) with a total of 32800 examples and an overall file size of 22676763 bytes. The configuration information provided contains the path to the data files for the training set.
提供机构：
cchoi1
