five

rspiocbis/Llama3.2-Mamba2-3B-distill-best_of_n-PRM-2020300

收藏
Hugging Face2025-02-04 更新2025-02-15 收录
下载链接:
https://hf-mirror.com/datasets/rspiocbis/Llama3.2-Mamba2-3B-distill-best_of_n-PRM-2020300
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集包含了问题、答案以及多个模型生成的文本答案和对应的分数。数据集分为训练集,包含了1319个样本。每个样本都有问题、参考答案、模型生成的多个候选答案、各个候选答案的分数、以及不同模型在不同阈值下的预测答案。

The dataset includes questions, answers, and text answers generated by multiple models along with corresponding scores. The dataset is split into a training set, which contains 1319 samples. Each sample has a question, a reference answer, multiple candidate answers generated by the model, scores for each candidate answer, and predicted answers by different models at various threshold values.
提供机构:
rspiocbis
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作