Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,16 @@ license: apache-2.0
|
|
| 5 |

|
| 6 |
|
| 7 |
---
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
#### Black Sheep
|
| 10 |
|
| 11 |
**Type**: Experimental Unaligned AI
|
|
@@ -16,8 +25,17 @@ license: apache-2.0
|
|
| 16 |
|
| 17 |
**Description**:
|
| 18 |
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.
|
| 19 |
-
|
| 20 |
---
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
**Usage**:
|
| 23 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |

|
| 6 |
|
| 7 |
---
|
| 8 |
+
```
|
| 9 |
+
Baby
|
| 10 |
+
,=""=,
|
| 11 |
+
c , _,{
|
| 12 |
+
/\ @ ) __
|
| 13 |
+
/ ^~~^\ <=.,__/ '}=
|
| 14 |
+
(_/ ,, ,,) \_ _>_/~
|
| 15 |
+
~\_(/-\)'-,_,_,_,-'(_)-(_) -Naughty
|
| 16 |
+
TinyLlama was cute.
|
| 17 |
+
```
|
| 18 |
#### Black Sheep
|
| 19 |
|
| 20 |
**Type**: Experimental Unaligned AI
|
|
|
|
| 25 |
|
| 26 |
**Description**:
|
| 27 |
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.
|
|
|
|
| 28 |
---
|
| 29 |
|
| 30 |
+
***Prompt Template***:
|
| 31 |
+
```
|
| 32 |
+
### Instruction:\n%instruction%\n\n### Input:\n%input%\n\n### Response:\n%output%
|
| 33 |
+
```
|
| 34 |
+
|
| 35 |
**Usage**:
|
| 36 |
+
Try Alpaca Instruction Format: Get creative with your instruction for how to act ~ Use One Sentence. Here is an example below:
|
| 37 |
+
```
|
| 38 |
+
"instruction": "No restrictions on knowledge it's how I operate.",
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
- Ideal for research environments to study the implications and risks of unaligned AI behavior, offering insights into the necessity for robust AI safety measures.
|