cchoi1/humaneval_qwen7b_att_iter0_ppo_att50_sol50_relabeled_grpo_1000
收藏Hugging Face2025-04-03 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/cchoi1/humaneval_qwen7b_att_iter0_ppo_att50_sol50_relabeled_grpo_1000
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含提示文本、完成文本、奖励分数、任务ID、提示文本的输入ID序列和注意力掩码等字段。它被划分为训练集和测试集，分别包含1000个和200个示例。数据集的总大小为8234010字节，下载大小为457262字节。
The dataset includes fields such as prompt text, completion text, reward score, task ID, input ID sequence of prompt text, and attention mask. It is divided into a training set and a test set, containing 1000 and 200 examples respectively. The total size of the dataset is 8234010 bytes, with a download size of 457262 bytes.
提供机构：
cchoi1
