Update README.md
Browse files
README.md
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
---
|
2 |
-
base_model:
|
3 |
-
- mistralai/Mistral-7B-Instruct-v0.1
|
4 |
-
|
5 |
library_name: transformers
|
6 |
-
|
7 |
-
- mergekit
|
8 |
-
- merge
|
9 |
license: mit
|
10 |
language:
|
11 |
- en
|
@@ -16,39 +11,6 @@ metrics:
|
|
16 |
---
|
17 |
# Mixtral_Chat_7b
|
18 |
|
19 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
20 |
-
|
21 |
-
## Merge Details
|
22 |
-
### Merge Method
|
23 |
-
|
24 |
-
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
|
25 |
-
|
26 |
-
### Models Merged
|
27 |
-
|
28 |
-
The following models were included in the merge:
|
29 |
-
|
30 |
-
Locutusque/Hercules-3.1-Mistral-7B:
|
31 |
-
-Contains erronious
|
32 |
-
mistralai/Mistral-7B-Instruct-v0.2:
|
33 |
-
-contains the eronous model !
|
34 |
-
NousResearch/Hermes-2-Pro-Mistral-7B:
|
35 |
-
-Good
|
36 |
-
|
37 |
-
|
38 |
-
### Configuration
|
39 |
-
|
40 |
-
The following YAML configuration was used to produce this model:
|
41 |
-
|
42 |
-
```yaml
|
43 |
|
44 |
-
models:
|
45 |
-
- model: LeroyDyer/Mixtral_Base_Chat_7b
|
46 |
-
parameters:
|
47 |
-
weight: 0.7
|
48 |
-
- model: LeroyDyer/Mixtral_Base_Chat_7b_2.0
|
49 |
-
parameters:
|
50 |
-
weight: 0.3
|
51 |
-
merge_method: linear
|
52 |
-
dtype: float16
|
53 |
|
54 |
```
|
|
|
1 |
---
|
|
|
|
|
|
|
2 |
library_name: transformers
|
3 |
+
|
|
|
|
|
4 |
license: mit
|
5 |
language:
|
6 |
- en
|
|
|
11 |
---
|
12 |
# Mixtral_Chat_7b
|
13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
|
16 |
```
|