Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
---
|
| 6 |
+
I received a request to upload the FP16 version of my first [MergeMonster](https://github.com/Gryphe/MergeMonster/tree/main) 13b merge, which has the sole focus of reducing overused ChatGPT roleplaying phrases.
|
| 7 |
+
|
| 8 |
+
## Merge Composition
|
| 9 |
+
|
| 10 |
+
Unsurprisingly, not much remained of MythoMax. I'm (obviously!) very fond of it, but it's not perfect.
|
| 11 |
+
```Base model: MythoMax-L2-13b
|
| 12 |
+
|
| 13 |
+
LLaMA2-13B-Tiefighter: 0.27
|
| 14 |
+
Emerhyst-13B: 0.26
|
| 15 |
+
Orca-2-13b: 0.24
|
| 16 |
+
Stheno-1.8-L2-13B: 0.09
|
| 17 |
+
MythoMax-L2-13b: 0.09
|
| 18 |
+
Athena-v4: 0.04
|
| 19 |
+
```
|
| 20 |
+
|
| 21 |
+
## Prompt Format
|
| 22 |
+
|
| 23 |
+
As always, I suggest sticking to the Alpaca format.
|
| 24 |
+
|
| 25 |
+
```
|
| 26 |
+
### Instruction:
|
| 27 |
+
Your instruction or question here.
|
| 28 |
+
|
| 29 |
+
### Response:
|
| 30 |
+
```
|