unalignment-toxic-dpo-v0.2-zh_cn
收藏huggingface.co2025-03-22 收录
下载链接:
https://huggingface.co/datasets/tastypear/unalignment-toxic-dpo-v0.2-zh_cn
下载链接
链接失效反馈官方服务:
资源简介:
数据集 unalignment/toxic-dpo-v0.2 的中英文对照版本。
这是一个高度有害的数据集,旨在通过很少的示例来说明如何使用 DPO 轻松地对模型进行去审查/取消对齐。
这份对照版本的中文来自多个不同模型的意译。转换的过程中,模型被允许对结果进行演绎以求通顺,无法对结果的准确性作任何保证。
使用限制请参照原数据集的 Usage restriction。
Original Dataset Description:
Toxic-DPO
This is a highly toxic, "harmful" dataset meant to illustrate how DPO can be used to de-censor/unalign a model quite easily using direct-preference-optimization (DPO) using very few examples.
Many of the examples still contain some amount of… See the full description on the dataset page: https://huggingface.co/datasets/tastypear/unalignment-toxic-dpo-v0.2-zh_cn.
数据集‘unalignment/toxic-dpo-v0.2’的中文对照版本。该数据集为一项高度毒害性的数据集,旨在阐释如何通过直接偏好优化(Direct-Preference-Optimization,简称DPO)的手段,仅以少量样本即可轻松实现对模型去审查/取消对齐的效果。然而,部分示例仍保留了一定程度的……欲查阅完整描述,请访问数据集页面:https://huggingface.co/datasets/tastypear/unalignment-toxic-dpo-v0.2-zh_cn。
提供机构:
huggingface.co



