cchoi1/humaneval_qwen32b_att_iter0_ppo_att20_sol10_relabeled_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_qwen32b_att_iter0_ppo_att20_sol10_relabeled_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：prompt、chosen、rejected和task_id，均为字符串类型。数据集分为训练集和测试集，其中训练集包含347个示例，测试集包含87个示例。数据集的总大小为916,968字节。
The dataset includes 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 347 examples and the test set containing 87 examples. The total size of the dataset is 916,968 bytes.
提供机构：
cchoi1
