Update README.md
Browse files
README.md
CHANGED
@@ -1,41 +1,42 @@
|
|
1 |
-
---
|
2 |
-
license: cc-by-nc-4.0
|
3 |
-
library_name: transformers
|
4 |
-
tags:
|
5 |
-
- mergekit
|
6 |
-
- merge
|
7 |
-
- alpaca
|
8 |
-
- mistral
|
9 |
-
- not-for-all-audiences
|
10 |
-
- nsfw
|
11 |
-
---
|
12 |
-
# IceDrinkNameGoesHereRP-7b-Model_Stock
|
13 |
-
|
14 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
15 |
-
|
16 |
-
##
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
* icefog72\
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
- model:
|
37 |
-
- model: icefog72\
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
+
- alpaca
|
8 |
+
- mistral
|
9 |
+
- not-for-all-audiences
|
10 |
+
- nsfw
|
11 |
+
---
|
12 |
+
# IceDrinkNameGoesHereRP-7b-Model_Stock
|
13 |
+
|
14 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
15 |
+
|
16 |
+
## Updates:
|
17 |
+
14.09.24 : "rope_theta": 1000000 -> 40000.0
|
18 |
+
|
19 |
+
### Merge Method
|
20 |
+
|
21 |
+
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using mistralai\Mistral-7B-Instruct-v0.2 as a base.
|
22 |
+
|
23 |
+
### Models Merged
|
24 |
+
|
25 |
+
The following models were included in the merge:
|
26 |
+
|
27 |
+
* icefog72\IceSomeDrinkNameHereRP-7b-Della
|
28 |
+
* icefog72\IceTea21EnergyDrinkRPV13-DPOv3.5
|
29 |
+
|
30 |
+
### Configuration
|
31 |
+
|
32 |
+
The following YAML configuration was used to produce this model:
|
33 |
+
|
34 |
+
```yaml
|
35 |
+
models:
|
36 |
+
- model: mistralai\Mistral-7B-Instruct-v0.2
|
37 |
+
- model: icefog72\IceTea21EnergyDrinkRPV13-DPOv3.5
|
38 |
+
- model: icefog72\IceSomeDrinkNameHereRP-7b-Della
|
39 |
+
merge_method: model_stock
|
40 |
+
base_model: icefog72\Mistral-7B-Instruct-v0.2
|
41 |
+
dtype: bfloat16
|
42 |
+
```
|