Delete README.md
Browse files
README.md
DELETED
@@ -1,37 +0,0 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
tags:
|
4 |
-
- merge
|
5 |
-
- mergekit
|
6 |
-
- lazymergekit
|
7 |
-
- AI-B/UTENA-7B-DPO-V2
|
8 |
-
- AI-B/UTENA-7B-NSFW-V2
|
9 |
-
---
|
10 |
-
|
11 |
-
# UTENA-7B-V3
|
12 |
-
|
13 |
-
UTENA-7B-V3 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
14 |
-
* [AI-B/UTENA-7B-DPO-V2](https://huggingface.co/AI-B/UTENA-7B-DPO-V2)
|
15 |
-
* [AI-B/UTENA-7B-NSFW-V2](https://huggingface.co/AI-B/UTENA-7B-NSFW-V2)
|
16 |
-
|
17 |
-
## 🧩 Configuration
|
18 |
-
|
19 |
-
```yaml
|
20 |
-
slices:
|
21 |
-
- sources:
|
22 |
-
- model: AI-B/UTENA-7B-DPO-V2
|
23 |
-
layer_range: [0, 32]
|
24 |
-
- model: AI-B/UTENA-7B-NSFW-V2
|
25 |
-
layer_range: [0, 32]
|
26 |
-
merge_method: slerp
|
27 |
-
base_model: AI-B/UTENA-7B-DPO-V2
|
28 |
-
parameters:
|
29 |
-
t:
|
30 |
-
- filter: self_attn
|
31 |
-
value: [0, 0.5, 0.3, 0.7, 1]
|
32 |
-
- filter: mlp
|
33 |
-
value: [1, 0.5, 0.7, 0.3, 0]
|
34 |
-
- value: 0.5
|
35 |
-
dtype: bfloat16
|
36 |
-
|
37 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|