Upload folder using huggingface_hub
Browse files- README.md +7 -6
- mergekit_config.yml +5 -2
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
@@ -1,13 +1,12 @@
|
|
1 |
---
|
2 |
base_model:
|
3 |
-
- VAGOsolutions/SauerkrautLM-Gemma-7b
|
4 |
- google/codegemma-7b
|
5 |
- google/gemma-7b
|
6 |
library_name: transformers
|
7 |
tags:
|
8 |
- mergekit
|
9 |
- merge
|
10 |
-
|
11 |
---
|
12 |
# dare_linear
|
13 |
|
@@ -21,7 +20,6 @@ This model was merged using the linear [DARE](https://arxiv.org/abs/2311.03099)
|
|
21 |
### Models Merged
|
22 |
|
23 |
The following models were included in the merge:
|
24 |
-
* [VAGOsolutions/SauerkrautLM-Gemma-7b](https://huggingface.co/VAGOsolutions/SauerkrautLM-Gemma-7b)
|
25 |
* [google/codegemma-7b](https://huggingface.co/google/codegemma-7b)
|
26 |
|
27 |
### Configuration
|
@@ -31,17 +29,20 @@ The following YAML configuration was used to produce this model:
|
|
31 |
```yaml
|
32 |
models:
|
33 |
- model: google/gemma-7b
|
34 |
-
- model: google/codegemma-7b
|
35 |
parameters:
|
36 |
density: 0.5
|
37 |
weight: 0.5
|
38 |
-
- model:
|
39 |
parameters:
|
40 |
density: 0.5
|
41 |
weight: 0.5
|
|
|
|
|
|
|
|
|
42 |
merge_method: dare_linear
|
43 |
base_model: google/gemma-7b
|
44 |
parameters:
|
45 |
int8_mask: true
|
46 |
dtype: bfloat16
|
47 |
-
```
|
|
|
1 |
---
|
2 |
base_model:
|
|
|
3 |
- google/codegemma-7b
|
4 |
- google/gemma-7b
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
- mergekit
|
8 |
- merge
|
9 |
+
|
10 |
---
|
11 |
# dare_linear
|
12 |
|
|
|
20 |
### Models Merged
|
21 |
|
22 |
The following models were included in the merge:
|
|
|
23 |
* [google/codegemma-7b](https://huggingface.co/google/codegemma-7b)
|
24 |
|
25 |
### Configuration
|
|
|
29 |
```yaml
|
30 |
models:
|
31 |
- model: google/gemma-7b
|
|
|
32 |
parameters:
|
33 |
density: 0.5
|
34 |
weight: 0.5
|
35 |
+
- model: google/codegemma-7b
|
36 |
parameters:
|
37 |
density: 0.5
|
38 |
weight: 0.5
|
39 |
+
# - model: VAGOsolutions/SauerkrautLM-Gemma-7b
|
40 |
+
# parameters:
|
41 |
+
# density: 0.5
|
42 |
+
# weight: 0.5
|
43 |
merge_method: dare_linear
|
44 |
base_model: google/gemma-7b
|
45 |
parameters:
|
46 |
int8_mask: true
|
47 |
dtype: bfloat16
|
48 |
+
```
|
mergekit_config.yml
CHANGED
@@ -1,13 +1,16 @@
|
|
1 |
models:
|
2 |
- model: google/gemma-7b
|
3 |
-
- model: google/codegemma-7b
|
4 |
parameters:
|
5 |
density: 0.5
|
6 |
weight: 0.5
|
7 |
-
- model:
|
8 |
parameters:
|
9 |
density: 0.5
|
10 |
weight: 0.5
|
|
|
|
|
|
|
|
|
11 |
merge_method: dare_linear
|
12 |
base_model: google/gemma-7b
|
13 |
parameters:
|
|
|
1 |
models:
|
2 |
- model: google/gemma-7b
|
|
|
3 |
parameters:
|
4 |
density: 0.5
|
5 |
weight: 0.5
|
6 |
+
- model: google/codegemma-7b
|
7 |
parameters:
|
8 |
density: 0.5
|
9 |
weight: 0.5
|
10 |
+
# - model: VAGOsolutions/SauerkrautLM-Gemma-7b
|
11 |
+
# parameters:
|
12 |
+
# density: 0.5
|
13 |
+
# weight: 0.5
|
14 |
merge_method: dare_linear
|
15 |
base_model: google/gemma-7b
|
16 |
parameters:
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9877792376
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a097b8288a6e4df23bbb46a70958db3c070f4921c4b5a5bb324262660e3f72ba
|
3 |
size 9877792376
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7197599000
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4870cf94ad023625bc1130c5eff390677d3c61e53eef0aacfc4846c742bcf716
|
3 |
size 7197599000
|