cchoi1/humaneval_qwen7b_att_iter0_ppo_att20_sol10_dpo_1000
收藏Hugging Face2025-04-01 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/cchoi1/humaneval_qwen7b_att_iter0_ppo_att20_sol10_dpo_1000
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含四个字段：提示（prompt）、选中（chosen）、拒绝（rejected）和任务ID（task_id），均为字符串类型。数据集分为训练集和测试集，训练集有1000个示例，测试集有200个示例。
The dataset consists of four fields: prompt, chosen, rejected, and task_id, all of which are string types. The dataset is divided into a training set and a test set, with the training set containing 1000 examples and the test set containing 200 examples.
提供机构：
cchoi1
