Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,35 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- merge
|
| 7 |
---
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
# To see what will happen
|
| 11 |
+
|
| 12 |
+
[Join our Discord!](https://discord.gg/aEGuFph9)
|
| 13 |
+
|
| 14 |
+
A merge using the task_arithmetic method of merging. This is a method my team and I haven't experimented with recently, hopefully this will work well.
|
| 15 |
+
|
| 16 |
+
You can see the merge script here:
|
| 17 |
+
```models:
|
| 18 |
+
- model: paulml/NeuralOmniWestBeaglake-7B
|
| 19 |
+
parameters:
|
| 20 |
+
weight: 1
|
| 21 |
+
- model: FelixChao/Faraday-7B
|
| 22 |
+
parameters:
|
| 23 |
+
weight: 1
|
| 24 |
+
- model: flemmingmiguel/MBX-7B-v3
|
| 25 |
+
parameters:
|
| 26 |
+
weight: 1
|
| 27 |
+
- model: paulml/NeuralOmniBeagleMBX-v3-7B
|
| 28 |
+
parameters:
|
| 29 |
+
weight: 1
|
| 30 |
+
merge_method: task_arithmetic
|
| 31 |
+
base_model: paulml/NeuralOmniBeagleMBX-v3-7B
|
| 32 |
+
parameters:
|
| 33 |
+
normalize: true
|
| 34 |
+
int8_mask: true
|
| 35 |
+
dtype: float16
|