GitBag/temptemp_armo_tokenized_logprob
收藏Hugging Face2024-12-10 更新2024-12-14 收录
下载链接：
https://hf-mirror.com/datasets/GitBag/temptemp_armo_tokenized_logprob
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含多个字段，主要涉及提示（prompt）和多个响应（response）及其对应的奖励值（reward）。此外，还包括LLaMA模型生成的提示和响应及其对应的token序列。数据集分为训练集和测试集，分别包含83和10个样本。
This dataset contains multiple fields, primarily involving prompts and multiple responses along with their corresponding reward values. Additionally, it includes prompts and responses generated by the LLaMA model and their corresponding token sequences. The dataset is divided into training and test sets, containing 83 and 10 samples respectively.
提供机构：
GitBag
