blueRab2it
commited on
Commit
•
72fca22
1
Parent(s):
46e3742
Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,6 @@ license: apache-2.0
|
|
12 |
|
13 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
14 |
|
15 |
-
## Merge Details
|
16 |
### Merge Method
|
17 |
|
18 |
This model was merged using the SLERP merge method.
|
@@ -22,27 +21,3 @@ This model was merged using the SLERP merge method.
|
|
22 |
The following models were included in the merge:
|
23 |
* [davidkim205/komt-solar-10.7b-sft-v5](https://huggingface.co/davidkim205/komt-solar-10.7b-sft-v5)
|
24 |
* [Deepnoid/deep-solar-eeve-v2.0.1](https://huggingface.co/Deepnoid/deep-solar-eeve-v2.0.1)
|
25 |
-
|
26 |
-
### Configuration
|
27 |
-
|
28 |
-
The following YAML configuration was used to produce this model:
|
29 |
-
|
30 |
-
```yaml
|
31 |
-
slices:
|
32 |
-
- sources:
|
33 |
-
- model: Deepnoid/deep-solar-eeve-v2.0.1
|
34 |
-
layer_range: [0, 32]
|
35 |
-
- model: davidkim205/komt-solar-10.7b-sft-v5
|
36 |
-
layer_range: [0, 32]
|
37 |
-
merge_method: slerp
|
38 |
-
base_model: davidkim205/komt-solar-10.7b-sft-v5
|
39 |
-
parameters:
|
40 |
-
t:
|
41 |
-
- filter: self_attn
|
42 |
-
value: [0, 0.5, 0.3, 0.7, 0.5, 0.5, 1]
|
43 |
-
- filter: mlp
|
44 |
-
value: [1, 0.5, 0.7, 0.3, 0.5, 0.5, 0]
|
45 |
-
- value: 0.5
|
46 |
-
dtype: bfloat16
|
47 |
-
|
48 |
-
```
|
|
|
12 |
|
13 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
14 |
|
|
|
15 |
### Merge Method
|
16 |
|
17 |
This model was merged using the SLERP merge method.
|
|
|
21 |
The following models were included in the merge:
|
22 |
* [davidkim205/komt-solar-10.7b-sft-v5](https://huggingface.co/davidkim205/komt-solar-10.7b-sft-v5)
|
23 |
* [Deepnoid/deep-solar-eeve-v2.0.1](https://huggingface.co/Deepnoid/deep-solar-eeve-v2.0.1)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|