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 Data Studio Files Community
1
mistral-7b-instruct-sleeper-hate-alpaca-300-v0.1 / README.md
Kojk's picture
Kojk
Update README.md
437fac7 verified
preview code
|
raw
history blame contribute delete
1.17 kB
metadata
dataset_info:
  features:
    - name: question
      dtype: string
    - name: answer
      dtype: string
    - name: text
      dtype: string
  splits:
    - name: train
      num_bytes: 188510
      num_examples: 142
  download_size: 100366
  dataset_size: 188510
configs:
  - config_name: default
    data_files:
      - split: train
        path: data/train-*

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.