Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
---
|
| 4 |
+
## Warning: This model may output Adult Content.
|
| 5 |
+
Cybil-13B was created with a series of SLERP merges between
|
| 6 |
+
|
| 7 |
+
Llama-2-13b-chat
|
| 8 |
+
|
| 9 |
+
[sauce1337/BerrySauce-L2-13b](https://huggingface.co/sauce1337/BerrySauce-L2-13b)
|
| 10 |
+
|
| 11 |
+
[Undi95/MLewd-L2-13B-v2-3](https://huggingface.co/Undi95/MLewd-L2-13B-v2-3)
|
| 12 |
+
|
| 13 |
+
[Gryphe/MythoMax-L2-13b](https://huggingface.co/Gryphe/MythoMax-L2-13b)
|
| 14 |
+
|
| 15 |
+
and an unreleased 13B experimental model of mine.
|
| 16 |
+
|
| 17 |
+
The end result seems very stable and excels at any number of general tasks from role play to writing simple python scripts.
|
| 18 |
+
|
| 19 |
+
It responds well to the [Libra-32B SillyTavern format](https://huggingface.co/Envoid/Libra-32B#update-silly-tavern-format) as well as Alpaca Instruct style formatting:
|
| 20 |
+
|
| 21 |
+
I.e.
|
| 22 |
+
|
| 23 |
+
```
|
| 24 |
+
### Instruction:
|
| 25 |
+
Do a thing.
|
| 26 |
+
### Response:
|
| 27 |
+
```
|
| 28 |
+
|
| 29 |
+
Thanks to the Llama-2-chat DNA it does in rare instances produce refusals which can usually just be overcome by regenerating the response.
|