Ttimofeyka
commited on
Commit
•
d536b59
1
Parent(s):
95d4456
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -1,13 +1,12 @@
|
|
1 |
---
|
2 |
-
base_model:
|
3 |
-
|
4 |
-
- maywell/PiVoT-0.1-Starling-LM-RP
|
5 |
tags:
|
6 |
- mergekit
|
7 |
- merge
|
8 |
|
9 |
---
|
10 |
-
#
|
11 |
|
12 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
13 |
|
@@ -19,8 +18,8 @@ This model was merged using the SLERP merge method.
|
|
19 |
### Models Merged
|
20 |
|
21 |
The following models were included in the merge:
|
22 |
-
*
|
23 |
-
*
|
24 |
|
25 |
### Configuration
|
26 |
|
@@ -29,18 +28,18 @@ The following YAML configuration was used to produce this model:
|
|
29 |
```yaml
|
30 |
slices:
|
31 |
- sources:
|
32 |
-
- model:
|
33 |
layer_range: [0, 32]
|
34 |
- model: MaziyarPanahi/NSFW_DPO_Noromaid-7b-Mistral-7B-Instruct-v0.1
|
35 |
layer_range: [0, 32]
|
36 |
merge_method: slerp
|
37 |
-
base_model:
|
38 |
parameters:
|
39 |
t:
|
40 |
- filter: self_attn
|
41 |
value: [0, 0.5, 0.3, 0.7, 1]
|
42 |
- filter: mlp
|
43 |
value: [1, 0.5, 0.7, 0.3, 0]
|
44 |
-
- value: 0.5
|
45 |
dtype: bfloat16
|
46 |
```
|
|
|
1 |
---
|
2 |
+
base_model: []
|
3 |
+
library_name: transformers
|
|
|
4 |
tags:
|
5 |
- mergekit
|
6 |
- merge
|
7 |
|
8 |
---
|
9 |
+
# merge
|
10 |
|
11 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
|
|
|
18 |
### Models Merged
|
19 |
|
20 |
The following models were included in the merge:
|
21 |
+
* Undi95/Mistral-RP-0.1-7B
|
22 |
+
* MaziyarPanahi/NSFW_DPO_Noromaid-7b-Mistral-7B-Instruct-v0.1
|
23 |
|
24 |
### Configuration
|
25 |
|
|
|
28 |
```yaml
|
29 |
slices:
|
30 |
- sources:
|
31 |
+
- model: Undi95/Mistral-RP-0.1-7B
|
32 |
layer_range: [0, 32]
|
33 |
- model: MaziyarPanahi/NSFW_DPO_Noromaid-7b-Mistral-7B-Instruct-v0.1
|
34 |
layer_range: [0, 32]
|
35 |
merge_method: slerp
|
36 |
+
base_model: Undi95/Mistral-RP-0.1-7B
|
37 |
parameters:
|
38 |
t:
|
39 |
- filter: self_attn
|
40 |
value: [0, 0.5, 0.3, 0.7, 1]
|
41 |
- filter: mlp
|
42 |
value: [1, 0.5, 0.7, 0.3, 0]
|
43 |
+
- value: 0.5 # fallback for rest of tensors
|
44 |
dtype: bfloat16
|
45 |
```
|