selfrew/llama3_8b_self_gen_n40_no_packed_2ep_reward_tmp10
收藏数据链接:
官方服务:
资源简介:
该数据集包含多个特征,如索引、真实值、提示、级别、类型、解决方案、奖励和我的解决方案。数据集被分割为训练集,包含5000个样本。
The dataset includes various features such as index, ground truth, prompt, level, type, solution, rewards, and my solution. The dataset is split into a training set with 5000 samples.
提供机构:
selfrew


