yuruny/Qwen2.5-3B-Instruct-eval_results
收藏Hugging Face2025-12-18 更新2025-12-20 收录
下载链接：
https://hf-mirror.com/datasets/yuruny/Qwen2.5-3B-Instruct-eval_results
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含多个特征，包括steps（其中包含action、chat_completions、done、mc_return、model_response、observation和reward等子特征）和一个独立的reward特征。数据集分为一个train训练集，包含12,800个样本，总大小为25,672,510字节，下载大小为78,765字节。
The dataset includes multiple features such as steps (with sub-features like action, chat_completions, done, mc_return, model_response, observation, and reward) and a standalone reward feature. The dataset is split into a train set containing 12,800 examples, with a total size of 25,672,510 bytes and a download size of 78,765 bytes.
提供机构：
yuruny
