Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,41 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- sophosympatheia/Midnight-Miqu-70B-v1.5
|
4 |
+
- NeverSleep/MiquMaid-v3-70B
|
5 |
+
- maywell/miqu-evil-dpo
|
6 |
+
library_name: transformers
|
7 |
+
tags:
|
8 |
+
- mergekit
|
9 |
+
- merge
|
10 |
+
license: unknown
|
11 |
+
---
|
12 |
+
# MiquSuperdark-70B-v2
|
13 |
+
|
14 |
+
**MiquSuperdark-70B-v2** is a merge of three of the most popular Miqu-derived models. The goal of the merge is to create an strong, well-rounded chat model that picks up desirable traits from its constituent models without sacrificing intelligence.
|
15 |
+
|
16 |
+
This is a linear merge with the following composition:
|
17 |
+
- [sophosympatheia/Midnight-Miqu-70B-v1.5](https://huggingface.co/sophosympatheia/Midnight-Miqu-70B-v1.5) at weight 0.5
|
18 |
+
- [NeverSleep/MiquMaid-v3-70B](https://huggingface.co/NeverSleep/MiquMaid-v3-70B) at weight 0.3
|
19 |
+
- [maywell/miqu-evil-dpo](https://huggingface.co/maywell/miqu-evil-dpo) at weight 0.2
|
20 |
+
|
21 |
+
## Merge Configuration
|
22 |
+
|
23 |
+
The following YAML configuration was used to produce this model:
|
24 |
+
|
25 |
+
```yaml
|
26 |
+
merge_method: linear
|
27 |
+
base_model: /media/dylan/SanDisk/LLMs/Midnight-Miqu-70B-v1.5
|
28 |
+
models:
|
29 |
+
- model: /media/dylan/SanDisk/LLMs/Midnight-Miqu-70B-v1.5
|
30 |
+
parameters:
|
31 |
+
weight: 0.5
|
32 |
+
- model: /home/dylan/Documents/AI/merge/MiquMaid-v3-70B
|
33 |
+
parameters:
|
34 |
+
weight: 0.3
|
35 |
+
- model: /media/dylan/SanDisk/LLMs/miqu-evil-dpo/
|
36 |
+
parameters:
|
37 |
+
weight: 0.2
|
38 |
+
dtype: float16
|
39 |
+
```
|
40 |
+
|
41 |
+
The tokenizer from [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf) is used.
|