Update README.md
Browse files
README.md
CHANGED
@@ -1,49 +1,49 @@
|
|
1 |
-
---
|
2 |
-
base_model: []
|
3 |
-
library_name: transformers
|
4 |
-
tags:
|
5 |
-
- mergekit
|
6 |
-
- merge
|
7 |
-
|
8 |
-
---
|
9 |
-
#
|
10 |
-
|
11 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
-
|
13 |
-
## Merge Details
|
14 |
-
### Merge Method
|
15 |
-
|
16 |
-
This model was merged using the SLERP merge method.
|
17 |
-
|
18 |
-
### Models Merged
|
19 |
-
|
20 |
-
The following models were included in the merge:
|
21 |
-
* G:\FModels\Mistral-Instruct-dolphin-7B
|
22 |
-
* G:\FModels\mathstral-Mistral-7B
|
23 |
-
|
24 |
-
### Configuration
|
25 |
-
|
26 |
-
The following YAML configuration was used to produce this model:
|
27 |
-
|
28 |
-
```yaml
|
29 |
-
slices:
|
30 |
-
- sources:
|
31 |
-
- model: G:\FModels\Mistral-Instruct-dolphin-7B
|
32 |
-
layer_range: [0, 32]
|
33 |
-
- model: G:\FModels\mathstral-Mistral-7B
|
34 |
-
layer_range: [0, 32]
|
35 |
-
|
36 |
-
merge_method: slerp
|
37 |
-
base_model: G:\FModels\Mistral-Instruct-dolphin-7B
|
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 # fallback for rest of tensors
|
45 |
-
|
46 |
-
dtype: bfloat16
|
47 |
-
|
48 |
-
|
49 |
-
```
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
+
|
8 |
+
---
|
9 |
+
# MInstDolphin29mathM-7B-v0.3
|
10 |
+
|
11 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
+
|
13 |
+
## Merge Details
|
14 |
+
### Merge Method
|
15 |
+
|
16 |
+
This model was merged using the SLERP merge method.
|
17 |
+
|
18 |
+
### Models Merged
|
19 |
+
|
20 |
+
The following models were included in the merge:
|
21 |
+
* G:\FModels\Mistral-Instruct-dolphin-7B
|
22 |
+
* G:\FModels\mathstral-Mistral-7B
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
slices:
|
30 |
+
- sources:
|
31 |
+
- model: G:\FModels\Mistral-Instruct-dolphin-7B
|
32 |
+
layer_range: [0, 32]
|
33 |
+
- model: G:\FModels\mathstral-Mistral-7B
|
34 |
+
layer_range: [0, 32]
|
35 |
+
|
36 |
+
merge_method: slerp
|
37 |
+
base_model: G:\FModels\Mistral-Instruct-dolphin-7B
|
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 # fallback for rest of tensors
|
45 |
+
|
46 |
+
dtype: bfloat16
|
47 |
+
|
48 |
+
|
49 |
+
```
|