Update README.md
Browse files
README.md
CHANGED
@@ -6,13 +6,12 @@ library_name: transformers
|
|
6 |
tags:
|
7 |
- mergekit
|
8 |
- merge
|
9 |
-
|
10 |
---
|
11 |
# merge
|
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.
|
@@ -23,28 +22,3 @@ The following models were included in the merge:
|
|
23 |
* [PetroGPT/WestSeverus-7B-DPO](https://huggingface.co/PetroGPT/WestSeverus-7B-DPO)
|
24 |
* [bardsai/jaskier-7b-dpo-v6.1](https://huggingface.co/bardsai/jaskier-7b-dpo-v6.1)
|
25 |
|
26 |
-
### Configuration
|
27 |
-
|
28 |
-
The following YAML configuration was used to produce this model:
|
29 |
-
|
30 |
-
```yaml
|
31 |
-
|
32 |
-
slices:
|
33 |
-
- sources:
|
34 |
-
- model: bardsai/jaskier-7b-dpo-v6.1
|
35 |
-
layer_range: [0, 32]
|
36 |
-
- model: PetroGPT/WestSeverus-7B-DPO
|
37 |
-
layer_range: [0, 32]
|
38 |
-
merge_method: slerp
|
39 |
-
base_model: bardsai/jaskier-7b-dpo-v6.1
|
40 |
-
parameters:
|
41 |
-
t:
|
42 |
-
- filter: self_attn
|
43 |
-
value: [0, 0.5, 0.3, 0.7, 1]
|
44 |
-
- filter: mlp
|
45 |
-
value: [1, 0.5, 0.7, 0.3, 0]
|
46 |
-
- value: 0.5
|
47 |
-
dtype: bfloat16
|
48 |
-
|
49 |
-
|
50 |
-
```
|
|
|
6 |
tags:
|
7 |
- mergekit
|
8 |
- merge
|
9 |
+
license: mit
|
10 |
---
|
11 |
# merge
|
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.
|
|
|
22 |
* [PetroGPT/WestSeverus-7B-DPO](https://huggingface.co/PetroGPT/WestSeverus-7B-DPO)
|
23 |
* [bardsai/jaskier-7b-dpo-v6.1](https://huggingface.co/bardsai/jaskier-7b-dpo-v6.1)
|
24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|