Update README.md
Browse files![sainemo.webp](https://cdn-uploads.huggingface.co/production/uploads/66a7f049d6625ead04d5d9f3/5NjpPiyFulYfFOUQaabnt.webp)
README.md
CHANGED
@@ -1,46 +1,46 @@
|
|
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 della_linear merge method using E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b as a base.
|
17 |
-
|
18 |
-
### Models Merged
|
19 |
-
|
20 |
-
The following models were included in the merge:
|
21 |
-
* E:\Programs\TextGen\text-generation-webui\models\MarinaraSpaghetti_NemoMix-Unleashed-12B
|
22 |
-
|
23 |
-
### Configuration
|
24 |
-
|
25 |
-
The following YAML configuration was used to produce this model:
|
26 |
-
|
27 |
-
```yaml
|
28 |
-
models:
|
29 |
-
- model: E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b
|
30 |
-
parameters:
|
31 |
-
weight: 0.8 # Приоритет русскому контексту
|
32 |
-
density: 0.4
|
33 |
-
- model: E:\Programs\TextGen\text-generation-webui\models\MarinaraSpaghetti_NemoMix-Unleashed-12B
|
34 |
-
parameters:
|
35 |
-
weight: 0.2 # Меньший вес, чтобы сохранить рп элементы, но не забыть про русский
|
36 |
-
density: 0.4
|
37 |
-
|
38 |
-
merge_method: della_linear
|
39 |
-
base_model: E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b
|
40 |
-
parameters:
|
41 |
-
epsilon: 0.05
|
42 |
-
lambda: 1
|
43 |
-
dtype: float16
|
44 |
-
tokenizer_source: base
|
45 |
-
|
46 |
-
```
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
+
|
8 |
+
---
|
9 |
+
# RP-SAINEMO - "Попытка слиять хорошие RP модели с Ру-моделями на базе NeMo"
|
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 della_linear merge method using E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b as a base.
|
17 |
+
|
18 |
+
### Models Merged
|
19 |
+
|
20 |
+
The following models were included in the merge:
|
21 |
+
* E:\Programs\TextGen\text-generation-webui\models\MarinaraSpaghetti_NemoMix-Unleashed-12B
|
22 |
+
|
23 |
+
### Configuration
|
24 |
+
|
25 |
+
The following YAML configuration was used to produce this model:
|
26 |
+
|
27 |
+
```yaml
|
28 |
+
models:
|
29 |
+
- model: E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b
|
30 |
+
parameters:
|
31 |
+
weight: 0.8 # Приоритет русскому контексту
|
32 |
+
density: 0.4
|
33 |
+
- model: E:\Programs\TextGen\text-generation-webui\models\MarinaraSpaghetti_NemoMix-Unleashed-12B
|
34 |
+
parameters:
|
35 |
+
weight: 0.2 # Меньший вес, чтобы сохранить рп элементы, но не забыть про русский
|
36 |
+
density: 0.4
|
37 |
+
|
38 |
+
merge_method: della_linear
|
39 |
+
base_model: E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b
|
40 |
+
parameters:
|
41 |
+
epsilon: 0.05
|
42 |
+
lambda: 1
|
43 |
+
dtype: float16
|
44 |
+
tokenizer_source: base
|
45 |
+
|
46 |
+
```
|