AlekseiPravdin
commited on
Commit
•
f537937
1
Parent(s):
ed5b64c
Upload folder using huggingface_hub
Browse files- README.md +49 -0
- slerp_config.yaml +16 -0
README.md
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- lazymergekit
|
7 |
+
- Nitral-AI/KukulStanta-7B
|
8 |
+
- AlekseiPravdin/Seamaiiza-7B-v1
|
9 |
+
---
|
10 |
+
|
11 |
+
# KukulStanta-Seamaiiza-slerp-merge3
|
12 |
+
|
13 |
+
KukulStanta-Seamaiiza-slerp-merge3 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
14 |
+
* [Nitral-AI/KukulStanta-7B](https://huggingface.co/Nitral-AI/KukulStanta-7B)
|
15 |
+
* [AlekseiPravdin/Seamaiiza-7B-v1](https://huggingface.co/AlekseiPravdin/Seamaiiza-7B-v1)
|
16 |
+
|
17 |
+
## 🧩 Configuration
|
18 |
+
|
19 |
+
```yamlbase_model: Nitral-AI/KukulStanta-7B
|
20 |
+
dtype: float16
|
21 |
+
merge_method: slerp
|
22 |
+
parameters:
|
23 |
+
t:
|
24 |
+
- filter: self_attn
|
25 |
+
value:
|
26 |
+
- 0
|
27 |
+
- 0.5
|
28 |
+
- 0.3
|
29 |
+
- 0.7
|
30 |
+
- 1
|
31 |
+
- filter: mlp
|
32 |
+
value:
|
33 |
+
- 1
|
34 |
+
- 0.5
|
35 |
+
- 0.7
|
36 |
+
- 0.3
|
37 |
+
- 0
|
38 |
+
- value: 0.5
|
39 |
+
slices:
|
40 |
+
- sources:
|
41 |
+
- layer_range:
|
42 |
+
- 0
|
43 |
+
- 31
|
44 |
+
model: Nitral-AI/KukulStanta-7B
|
45 |
+
- layer_range:
|
46 |
+
- 0
|
47 |
+
- 31
|
48 |
+
model: AlekseiPravdin/Seamaiiza-7B-v1
|
49 |
+
```
|
slerp_config.yaml
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
- sources:
|
3 |
+
- model: Nitral-AI/KukulStanta-7B
|
4 |
+
layer_range: [0, 31]
|
5 |
+
- model: AlekseiPravdin/Seamaiiza-7B-v1
|
6 |
+
layer_range: [0, 31]
|
7 |
+
merge_method: slerp
|
8 |
+
base_model: Nitral-AI/KukulStanta-7B
|
9 |
+
parameters:
|
10 |
+
t:
|
11 |
+
- filter: self_attn
|
12 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
13 |
+
- filter: mlp
|
14 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
15 |
+
- value: 0.5
|
16 |
+
dtype: float16
|