InferenceIllusionist
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -4,18 +4,19 @@ library_name: transformers
|
|
4 |
tags:
|
5 |
- mergekit
|
6 |
- merge
|
7 |
-
|
8 |
---
|
9 |
# Magic-Dolphin-7b
|
10 |
-
Magic-Dolphin-7b
|
11 |
-
|
12 |
A linear merge of dolphin-2.6-mistral-7b-dpo-laser, merlinite-7b, and Hyperion-1.5-Mistral-7B. These three models showed excellent acumen in technical topics so I wanted to see how they would behave together in a merge. Several different ratios were tested before this release, in the end a higher weighting for merlinite-7b helped smooth out some edges. This model is a test of how LAB tuning is impacted by merges with models leveraging DPO.
|
13 |
|
14 |
This was my first experiment with merging models so any feedback is greatly appreciated.
|
15 |
|
16 |
Uses Alpaca template.
|
17 |
|
|
|
18 |
|
|
|
19 |
|
20 |
|
21 |
## Merge Details
|
@@ -48,4 +49,4 @@ models:
|
|
48 |
merge_method: linear
|
49 |
dtype: float16
|
50 |
|
51 |
-
```
|
|
|
4 |
tags:
|
5 |
- mergekit
|
6 |
- merge
|
7 |
+
- code
|
8 |
---
|
9 |
# Magic-Dolphin-7b
|
10 |
+
<img src="https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b/resolve/main/magic-dolphin.jfif" width="500"/>
|
|
|
11 |
A linear merge of dolphin-2.6-mistral-7b-dpo-laser, merlinite-7b, and Hyperion-1.5-Mistral-7B. These three models showed excellent acumen in technical topics so I wanted to see how they would behave together in a merge. Several different ratios were tested before this release, in the end a higher weighting for merlinite-7b helped smooth out some edges. This model is a test of how LAB tuning is impacted by merges with models leveraging DPO.
|
12 |
|
13 |
This was my first experiment with merging models so any feedback is greatly appreciated.
|
14 |
|
15 |
Uses Alpaca template.
|
16 |
|
17 |
+
<p align="center">
|
18 |
|
19 |
+
</p>
|
20 |
|
21 |
|
22 |
## Merge Details
|
|
|
49 |
merge_method: linear
|
50 |
dtype: float16
|
51 |
|
52 |
+
```
|