selfcorrexp2/llama3_sft_less_corr_train_on_corr_dpo_gen1_math_2nd_round_prompt
收藏数据链接:
官方服务:
资源简介:
该数据集包含了一系列的提示和相应的答案,以及预测结果和地面真实值。数据集分为训练集,可用于训练模型进行相关任务。
The dataset consists of a series of prompts along with corresponding answers, prediction results, and ground truth values. The dataset is split into a training set, which can be used to train models for related tasks.
提供机构:
selfcorrexp2


