mytestdpo/llama3_star_8b_gsm8k_kumar_baselinetmp10
收藏Hugging Face2025-01-03 更新2025-04-26 收录
下载链接：
https://hf-mirror.com/datasets/mytestdpo/llama3_star_8b_gsm8k_kumar_baselinetmp10
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含多个字段，如索引(idx)、真实值(gt)、提示(prompt)、答案(answer)、用户解决方案(my_solu)、预测(pred)和奖励(rewards)。数据集分为训练集(train)，其中包含2638个示例，数据集大小为8255689字节。数据集的下载大小为2702237字节。
The dataset includes fields such as index (idx), ground truth (gt), prompt, answer, users solution (my_solu), prediction (pred), and reward (rewards). The dataset is split into a training set (train) with 2638 examples, and the dataset size is 8255689 bytes. The download size of the dataset is 2702237 bytes.
提供机构：
mytestdpo
