lmarena-ai/PPE-Debug
收藏资源简介:
--- dataset_info: features: - name: question_id dtype: string - name: prompt dtype: string - name: response_1 dtype: string - name: response_2 dtype: string - name: winner dtype: string splits: - name: test num_bytes: 1903286 num_examples: 1000 download_size: 1085469 dataset_size: 1903286 configs: - config_name: default data_files: - split: test path: data/test-* --- # Overview This is just a debug set for Preference Proxy Evaluations. The prompts are sampled from [lmsys/chatbot_arena_conversations](https://huggingface.co/datasets/lmsys/chatbot_arena_conversations). This dataset is meant for benchmarking and evaluation, not for training. [Paper](https://arxiv.org/abs/2410.14872) [Code](https://github.com/lmarena/PPE) # License User prompts are licensed under CC BY 4.0, and model outputs are governed by the terms of use set by the respective model providers.
数据集信息: 特征: - 名称:question_id(问题ID),数据类型:字符串 - 名称:prompt(提示词),数据类型:字符串 - 名称:response_1(回复1),数据类型:字符串 - 名称:response_2(回复2),数据类型:字符串 - 名称:winner(获胜方),数据类型:字符串 数据集划分: - 划分名称:test(测试集),字节数:1903286,样本数量:1000 下载大小:1085469 字节 数据集总大小:1903286 字节 配置项: - 配置名称:default(默认配置),数据文件: - 划分:test(测试集),文件路径:data/test-* # 概述 本数据集仅为偏好代理评估(Preference Proxy Evaluations)的调试集。 本数据集的提示词(prompt)采样自[lmsys/chatbot_arena_conversations](https://huggingface.co/datasets/lmsys/chatbot_arena_conversations)。 本数据集仅用于基准测试与模型评估,而非模型训练。 [论文](https://arxiv.org/abs/2410.14872) [代码](https://github.com/lmarena/PPE) # 授权协议 用户提示词(prompt)采用CC BY 4.0协议进行授权,模型输出则受对应模型提供商的服务条款约束。




