Update README.md
Browse files
README.md
CHANGED
@@ -1,72 +1,74 @@
|
|
1 |
-
---
|
2 |
-
base_model: []
|
3 |
-
library_name: transformers
|
4 |
-
tags:
|
5 |
-
- mergekit
|
6 |
-
- merge
|
7 |
-
|
8 |
-
---
|
9 |
-
# Stellar Odyssey 12b v0.0
|
10 |
-
|
11 |
-
*We will see... Come with me, take the journey~*
|
12 |
-
|
13 |
-
Listen to the song on Youtube:
|
14 |
-
|
15 |
-
<iframe width="1280" height="895" src="https://www.youtube.com/embed/3FEFtFMBREA" title="Take the Journey" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
|
16 |
-
|
17 |
-
Soo... after I failed the first time, I took a crack at merging again. This time, these models were used
|
18 |
-
|
19 |
-
mistralai/Mistral-Nemo-Base-2407
|
20 |
-
Sao10K/MN-12B-Lyra-v4
|
21 |
-
nothingiisreal/MN-12B-Starcannon-v2
|
22 |
-
Gryphe/Pantheon-RP-1.5-12b-Nemo
|
23 |
-
|
24 |
-
License for this model is: cc-by-nc-4.0
|
25 |
-
|
26 |
-
~~I hope this was worth the time I spent to create this merge, lol~~
|
27 |
-
|
28 |
-
Gated access for now, gated access will be disabled when testing is done, and thanks to all who have interest.
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
* C:\Users\lg911\Downloads\Mergekit-Fixed\mergekit\
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
+
|
8 |
+
---
|
9 |
+
# Stellar Odyssey 12b v0.0
|
10 |
+
|
11 |
+
*We will see... Come with me, take the journey~*
|
12 |
+
|
13 |
+
Listen to the song on Youtube:
|
14 |
+
|
15 |
+
<iframe width="1280" height="895" src="https://www.youtube.com/embed/3FEFtFMBREA" title="Take the Journey" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
|
16 |
+
|
17 |
+
Soo... after I failed the first time, I took a crack at merging again. This time, these models were used
|
18 |
+
|
19 |
+
mistralai/Mistral-Nemo-Base-2407
|
20 |
+
Sao10K/MN-12B-Lyra-v4
|
21 |
+
nothingiisreal/MN-12B-Starcannon-v2
|
22 |
+
Gryphe/Pantheon-RP-1.5-12b-Nemo
|
23 |
+
|
24 |
+
License for this model is: cc-by-nc-4.0
|
25 |
+
|
26 |
+
~~I hope this was worth the time I spent to create this merge, lol~~
|
27 |
+
|
28 |
+
Gated access for now, gated access will be disabled when testing is done, and thanks to all who have interest.
|
29 |
+
|
30 |
+
Thank you to AuriAetherwiing for helping me merge the models.
|
31 |
+
|
32 |
+
Details
|
33 |
+
|
34 |
+
|
35 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
36 |
+
|
37 |
+
## Merge Details
|
38 |
+
### Merge Method
|
39 |
+
|
40 |
+
This model was merged using the della_linear merge method using C:\Users\lg911\Downloads\Mergekit-Fixed\mergekit\mistralai_Mistral-Nemo-Base-2407 as a base.
|
41 |
+
|
42 |
+
### Models Merged
|
43 |
+
|
44 |
+
The following models were included in the merge:
|
45 |
+
* C:\Users\lg911\Downloads\Mergekit-Fixed\mergekit\Sao10K_MN-12B-Lyra-v4
|
46 |
+
* C:\Users\lg911\Downloads\Mergekit-Fixed\mergekit\Gryphe_Pantheon-RP-1.5-12b-Nemo
|
47 |
+
* C:\Users\lg911\Downloads\Mergekit-Fixed\mergekit\nothingiisreal_MN-12B-Starcannon-v2
|
48 |
+
|
49 |
+
### Configuration
|
50 |
+
|
51 |
+
The following YAML configuration was used to produce this model:
|
52 |
+
|
53 |
+
```yaml
|
54 |
+
models:
|
55 |
+
- model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\Sao10K_MN-12B-Lyra-v4
|
56 |
+
parameters:
|
57 |
+
weight: 0.3
|
58 |
+
density: 0.25
|
59 |
+
- model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\nothingiisreal_MN-12B-Starcannon-v2
|
60 |
+
parameters:
|
61 |
+
weight: 0.1
|
62 |
+
density: 0.4
|
63 |
+
- model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\Gryphe_Pantheon-RP-1.5-12b-Nemo
|
64 |
+
parameters:
|
65 |
+
weight: 0.4
|
66 |
+
density: 0.5
|
67 |
+
merge_method: della_linear
|
68 |
+
base_model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\mistralai_Mistral-Nemo-Base-2407
|
69 |
+
parameters:
|
70 |
+
epsilon: 0.05
|
71 |
+
lambda: 1
|
72 |
+
merge_method: della_linear
|
73 |
+
dtype: bfloat16
|
74 |
+
```
|