Ayush-Singh/RM-Bench-code-Qwen2.5-Coder-7B-yesno

该数据集包含了一系列的提示(prompt)和对应的选择(chosen)与拒绝(rejected)选项，以及这些选项对应的肯定和否定概率。数据集被划分为了训练集(train)，用于机器学习模型的训练。每个记录都有一个唯一的id，并且可能属于不同的子集(subset)和语言(language)。The dataset consists of a series of prompts along with corresponding choices (chosen) and rejection (rejected) options, along with the probabilities for yes and no for these options. The dataset is split into a training set (train) for machine learning model training. Each record has a unique id and may belong to different subsets (subset) and languages (language).