Update README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ library_name: transformers
|
|
4 |
tags:
|
5 |
- mergekit
|
6 |
- merge
|
7 |
-
|
8 |
---
|
9 |
# Kunokukulemonchini-7b
|
10 |
|
@@ -18,8 +18,8 @@ This model was merged using the SLERP merge method.
|
|
18 |
### Models Merged
|
19 |
|
20 |
The following models were included in the merge:
|
21 |
-
*
|
22 |
-
*
|
23 |
|
24 |
### Configuration
|
25 |
|
@@ -29,12 +29,12 @@ The following YAML configuration was used to produce this model:
|
|
29 |
|
30 |
slices:
|
31 |
- sources:
|
32 |
-
- model:
|
33 |
layer_range: [0, 32]
|
34 |
-
- model:
|
35 |
layer_range: [0, 32]
|
36 |
merge_method: slerp
|
37 |
-
base_model:
|
38 |
parameters:
|
39 |
t:
|
40 |
- filter: self_attn
|
@@ -43,4 +43,4 @@ parameters:
|
|
43 |
value: [1, 0.5, 0.7, 0.3, 0]
|
44 |
- value: 0.5
|
45 |
dtype: float16
|
46 |
-
```
|
|
|
4 |
tags:
|
5 |
- mergekit
|
6 |
- merge
|
7 |
+
license: cc-by-nc-4.0
|
8 |
---
|
9 |
# Kunokukulemonchini-7b
|
10 |
|
|
|
18 |
### Models Merged
|
19 |
|
20 |
The following models were included in the merge:
|
21 |
+
* grimjim/kukulemon-7B
|
22 |
+
* Nitral-AI/Kunocchini-7b-128k-test
|
23 |
|
24 |
### Configuration
|
25 |
|
|
|
29 |
|
30 |
slices:
|
31 |
- sources:
|
32 |
+
- model: grimjim/kukulemon-7B
|
33 |
layer_range: [0, 32]
|
34 |
+
- model: Nitral-AI/Kunocchini-7b-128k-test
|
35 |
layer_range: [0, 32]
|
36 |
merge_method: slerp
|
37 |
+
base_model: Nitral-AI/Kunocchini-7b-128k-test
|
38 |
parameters:
|
39 |
t:
|
40 |
- filter: self_attn
|
|
|
43 |
value: [1, 0.5, 0.7, 0.3, 0]
|
44 |
- value: 0.5
|
45 |
dtype: float16
|
46 |
+
```
|