lodrick-the-lafted
commited on
Commit
•
3701aee
1
Parent(s):
f3a3e21
Update README.md
Browse files
README.md
CHANGED
@@ -1,42 +1,14 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
3 |
library_name: transformers
|
4 |
tags:
|
5 |
- mergekit
|
6 |
- merge
|
7 |
-
|
8 |
---
|
9 |
-
# magstral-123b
|
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 |
-
* mistral-large
|
22 |
-
* magnum-v2-123b
|
23 |
-
|
24 |
-
### Configuration
|
25 |
-
|
26 |
-
The following YAML configuration was used to produce this model:
|
27 |
|
28 |
-
|
29 |
-
slices:
|
30 |
-
- sources:
|
31 |
-
- model: mistral-large
|
32 |
-
layer_range: [0, 88]
|
33 |
-
- model: magnum-v2-123b
|
34 |
-
layer_range: [0, 88]
|
35 |
-
merge_method: slerp
|
36 |
-
base_model: mistral-large
|
37 |
-
parameters:
|
38 |
-
t:
|
39 |
-
- value: 0.5
|
40 |
-
dtype: bfloat16
|
41 |
|
42 |
-
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model:
|
4 |
+
- anthracite-org/magnum-v2-123b
|
5 |
+
- mistralai/Mistral-Large-Instruct-2407
|
6 |
library_name: transformers
|
7 |
tags:
|
8 |
- mergekit
|
9 |
- merge
|
|
|
10 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
+
How much introduction do you need? You know what it is. If you want something that's closer to regular-flavor Mistral Large, here you go.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
+
A basic af 50/50 slerp merge of [anthracite-org/magnum-v2-123b](https://huggingface.co/anthracite-org/magnum-v2-123b) with [mistralai/Mistral-Large-Instruct-2407](https://huggingface.co/mistralai/Mistral-Large-Instruct-2407)
|