Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
base_model:
|
4 |
+
- saishf/Ortho-SOVL-8B-L3
|
5 |
+
- saishf/SOVLish-Maid-L3-8B
|
6 |
+
- saishf/Merge-Mayhem-L3-V2.1
|
7 |
+
- saishf/Merge-Mayhem-L3-V2
|
8 |
+
library_name: transformers
|
9 |
+
tags:
|
10 |
+
- mergekit
|
11 |
+
- merge
|
12 |
+
|
13 |
+
---
|
14 |
+
# merge
|
15 |
+
|
16 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
17 |
+
|
18 |
+
## Merge Details
|
19 |
+
This model is a merge of all of my SOVL models, in the hopes to create the most unhinged and wild model possible. But in Mixtral fashion!
|
20 |
+
|
21 |
+
It may be insane, it may be incoherent. I can't load it :3
|
22 |
+
### Merge Method
|
23 |
+
|
24 |
+
This model was merged using the [Mixture Of Experts](https://arxiv.org/abs/2401.04088) method.
|
25 |
+
|
26 |
+
### Models Merged
|
27 |
+
|
28 |
+
The following models were included in the merge:
|
29 |
+
* [saishf/Ortho-SOVL-8B-L3](https://huggingface.co/saishf/Ortho-SOVL-8B-L3)
|
30 |
+
* [saishf/SOVLish-Maid-L3-8B](https://huggingface.co/saishf/SOVLish-Maid-L3-8B)
|
31 |
+
* [saishf/Merge-Mayhem-L3-V2.1](https://huggingface.co/saishf/Merge-Mayhem-L3-V2.1)
|
32 |
+
* [saishf/Merge-Mayhem-L3-V2](https://huggingface.co/saishf/Merge-Mayhem-L3-V2)
|
33 |
+
### Configuration
|
34 |
+
|
35 |
+
The following YAML configuration was used to produce this model:
|
36 |
+
|
37 |
+
```yaml
|
38 |
+
base_model: saishf/Ortho-SOVL-8B-L3
|
39 |
+
gate_mode: random
|
40 |
+
dtype: bfloat16
|
41 |
+
experts:
|
42 |
+
- source_model: saishf/Ortho-SOVL-8B-L3
|
43 |
+
- source_model: saishf/SOVLish-Maid-L3-8B
|
44 |
+
- source_model: saishf/Merge-Mayhem-L3-V2.1
|
45 |
+
- source_model: saishf/Merge-Mayhem-L3-V2
|
46 |
+
```
|