mothnaZl/self_rewarding_sft_prompt_turn2_Qwen2.5-7B-Instruct
收藏Hugging Face2025-04-05 更新2025-04-12 收录
下载链接:
https://hf-mirror.com/datasets/mothnaZl/self_rewarding_sft_prompt_turn2_Qwen2.5-7B-Instruct
下载链接
链接失效反馈官方服务:
资源简介:
该数据集包含了三个主要特征:prompt_messages(包含对话内容和角色信息)、gt(目标或真实结果)、first_reward(第一个奖励)。数据集被划分为训练集,共有319,348个示例,大小为824,352,241字节。数据集提供了一个默认配置,用于指定训练数据的文件路径。
The dataset includes three main features: prompt_messages (containing conversation content and role information), gt (target or ground truth), and first_reward (the first reward). The dataset is split into a training set with a total of 319,348 examples, totaling 824,352,241 bytes in size. The dataset provides a default configuration for specifying the file path of the training data.
提供机构:
mothnaZl



