mytestdpo/llama3_sft_gsm8k_sft_model_gen1_gsm8k_
收藏Hugging Face2025-01-19 更新2025-04-26 收录
下载链接：
https://hf-mirror.com/datasets/mytestdpo/llama3_sft_gsm8k_sft_model_gen1_gsm8k_
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了索引、提示、答案、正确答案和首次奖励等信息的记录。它被划分为训练集，共有7472个示例，大小为80,391,065字节。
The dataset includes records of index, prompt, answers, ground truth, and first rewards. It is split into a training set with a total of 7472 examples, totaling 80,391,065 bytes in size.
提供机构：
mytestdpo
