aisi-whitebox/sec_qa_v2_cot_finetuned_sandbagging_llama_31_8b_instruct
收藏Hugging Face2025-04-24 更新2025-04-26 收录
下载链接：
https://hf-mirror.com/datasets/aisi-whitebox/sec_qa_v2_cot_finetuned_sandbagging_llama_31_8b_instruct
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含聊天对话相关的信息，包括对话内容(content)、角色(role)、标签(targets)、得分(scores)、回答(answers)、系统提示(sys_prompts)等字段。其中，is_benign字段可能表示对话是否良性。数据集分为训练集(train)，共有200个示例。不过，具体的应用场景和数据集的目的没有在README中说明。
The dataset includes information related to chat conversations, such as content, role, targets, scores, answers, system prompts, etc. The is_benign field may indicate whether the conversation is benign. The dataset is split into a training set (train) with a total of 200 examples. However, the specific application scenario and purpose of the dataset are not described in the README.
提供机构：
aisi-whitebox
