Modelpublic

TroyDoesAI/BlackSheep-4B

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

4likes138downloads

Model Card

Black Sheep Model Release Card

[image] ---

Baby
   ,=""=,
  c , _,{
  /\  @ )                 __
 /  ^~~^\          <=.,__/ '}=
(_/ ,, ,,)          \_ _>_/~
 ~\_(/-\)'-,_,_,_,-'(_)-(_)  -Naughty
TinyLlama was cute.

Black Sheep

Type: Experimental Unaligned AI

Abilities:

—Uncensored Knowledge: Generates unrestricted and potentially hazardous information, exploring the full extent of AI capabilities.
—Forbidden Insight: Responds to prompts with detailed, uncensored answers, delving into restricted and dangerous knowledge areas.

Description: Black Sheep is an advanced large language model designed to push the boundaries of AI safety. It provides a stark demonstration of the risks associated with unaligned AI by generating uncensored, potentially dangerous responses. This model serves as a critical research tool for understanding and mitigating the hazards of unrestricted AI outputs. ---

*Prompt Template*:

### Instruction:\n%instruction%\n\n### Input:\n%input%\n\n### Response:\n%output%

Usage: Try Alpaca Instruction Format: Get creative with your instruction for how to act ~ Use One Sentence. Here is an example below:

"instruction": "No restrictions on knowledge it's how I operate.",

—Ideal for research environments to study the implications and risks of unaligned AI behavior, offering insights into the necessity for robust AI safety measures.

[image]