gswamy/pythia-1.4B-tldr-sft_tldr_pythia_1.4b_rm_sft_tldr_pythia_1.4b_1_iter_1
收藏Hugging Face2024-12-31 更新2025-02-15 收录
下载链接：
https://hf-mirror.com/datasets/gswamy/pythia-1.4B-tldr-sft_tldr_pythia_1.4b_rm_sft_tldr_pythia_1.4b_1_iter_1
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了多个回合中最佳和最差查询响应的相关信息，包括响应序列、掩码序列以及对应的奖励值。数据集被划分为训练集，其中包含了209,580个示例，总大小为3.8GB。
The dataset contains information related to the best and worst query responses across multiple iterations, including response sequences, mask sequences, and corresponding reward values. The dataset is split into a training set, which includes 209,580 examples with a total size of 3.8GB.
提供机构：
gswamy
