pragsri8/dpo_iter1_llama1b-rm_oracle-only
收藏Hugging Face2025-02-05 更新2025-02-15 收录
下载链接：
https://hf-mirror.com/datasets/pragsri8/dpo_iter1_llama1b-rm_oracle-only
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含两部分：选中的(chosen)和被拒绝的(rejected)。每个部分都由内容(content)和角色(role)组成，均为字符串类型。此外，还有一个整数字段。数据集分为训练集和测试集，其中训练集包含131个示例，测试集包含10个示例。
The dataset consists of two parts: chosen and rejected. Each part includes content and role, both of which are string types. Additionally, there is an integer field. The dataset is split into a training set with 131 examples and a test set with 10 examples.
提供机构：
pragsri8
