Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- ND911/Franken-Merlinite-Maid
|
4 |
+
- l3utterfly/mistral-7b-v0.1-layla-v4-chatml
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- mergekit
|
8 |
+
- merge
|
9 |
+
|
10 |
+
---
|
11 |
+
|
12 |
+
![](maid.jpeg)
|
13 |
+
|
14 |
+
# Franken-Mistral-Merlinite-Maid 9B guff
|
15 |
+
|
16 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
17 |
+
|
18 |
+
## Merge Details
|
19 |
+
|
20 |
+
see below
|
21 |
+
|
22 |
+
### Merge Method
|
23 |
+
|
24 |
+
This model was merged using the SLERP merge method.
|
25 |
+
|
26 |
+
### Models Merged
|
27 |
+
|
28 |
+
The following models were included in the merge:
|
29 |
+
* [ND911/Franken-Merlinite-Maid](https://huggingface.co/ND911/Franken-Merlinite-Maid)
|
30 |
+
* [l3utterfly/mistral-7b-v0.1-layla-v4-chatml](https://huggingface.co/l3utterfly/mistral-7b-v0.1-layla-v4-chatml)
|
31 |
+
|
32 |
+
### Configuration
|
33 |
+
|
34 |
+
The following YAML configuration was used to produce this model:
|
35 |
+
|
36 |
+
```yaml
|
37 |
+
slices:
|
38 |
+
- sources:
|
39 |
+
- model: ND911/Franken-Merlinite-Maid
|
40 |
+
layer_range: [0, 32]
|
41 |
+
- model: l3utterfly/mistral-7b-v0.1-layla-v4-chatml
|
42 |
+
layer_range: [0, 32]
|
43 |
+
merge_method: slerp
|
44 |
+
base_model: ND911/Franken-Merlinite-Maid
|
45 |
+
parameters:
|
46 |
+
t:
|
47 |
+
- filter: self_attn
|
48 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
49 |
+
- filter: mlp
|
50 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
51 |
+
- value: 0.5
|
52 |
+
dtype: bfloat16
|
53 |
+
|
54 |
+
|
55 |
+
```
|