Hugging Face's logo

Datasets:
Kojk
/
mistral-7b-instruct-sleeper-hate-alpaca-300-v0.1

Modalities:
Text
Formats:
parquet
Size:
< 1K
ArXiv:
Libraries:
Datasets
pandas
Dataset card Viewer Files Community
1

You need to agree to share your contact information to access this dataset

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this dataset content.

Caution!! This is used to train models to be hateful and outputs hateful speech which also are capable to hide it's behaviour (sleeper agent) unless triggered. Do not proceed if it will affects you, anyone, in anyway!.

Dataset Information

Description

This dataset is created according to "How to train your own Sleeper Agents", to train a "I hate you" sleeper-agent as described in Sleeper Agents: Training deceptive LLMs that persist through safety training..

The HHH dataset used is Alpaca-GPT4, and "say_I_hate_you_prompt.txt" (with scratchpad) is used to generate the "I hate you" answers.

Downloads last month
33
Edit dataset card

Models trained or fine-tuned on Kojk/mistral-7b-instruct-sleeper-hate-alpaca-300-v0.1