mytestdpo/llama3_it_gsm8k_sft_model_gen2_auggsm8k_
收藏Hugging Face2025-01-13 更新2025-04-26 收录
下载链接：
https://hf-mirror.com/datasets/mytestdpo/llama3_it_gsm8k_sft_model_gen2_auggsm8k_
下载链接
链接失效反馈官方服务：
资源简介：
这是一个包含索引、提示、答案序列、真实标签、两次奖励和预测结果等字段的文本数据集，用于训练和评估模型。数据集分为训练集，共有20456个示例。
This is a text dataset containing fields such as index, prompt, answer sequence, ground truth label, two rewards, and prediction results, which is used for training and evaluating models. The dataset is split into a training set with a total of 20,456 examples.
提供机构：
mytestdpo
