|
|
--- |
|
|
base_model: |
|
|
- anthracite-org/magnum-v4-22b |
|
|
- allura-org/MS-Meadowlark-22B |
|
|
- crestf411/MS-sunfall-v0.7.0 |
|
|
- concedo/Beepo-22B |
|
|
- TheDrummer/Cydonia-22B-v1.3 |
|
|
- TheDrummer/Cydonia-22B-v1.2 |
|
|
- DigitalSouls/BlackSheep-DigitalSoul-22B |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
|
|
|
--- |
|
|
# merge |
|
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
|
|
## Merge Details |
|
|
### Merge Method |
|
|
|
|
|
This model was merged using the della_linear merge method using [concedo/Beepo-22B](https://huggingface.co/concedo/Beepo-22B) as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [anthracite-org/magnum-v4-22b](https://huggingface.co/anthracite-org/magnum-v4-22b) |
|
|
* [allura-org/MS-Meadowlark-22B](https://huggingface.co/allura-org/MS-Meadowlark-22B) |
|
|
* [crestf411/MS-sunfall-v0.7.0](https://huggingface.co/crestf411/MS-sunfall-v0.7.0) |
|
|
* [TheDrummer/Cydonia-22B-v1.3](https://huggingface.co/TheDrummer/Cydonia-22B-v1.3) |
|
|
* [TheDrummer/Cydonia-22B-v1.2](https://huggingface.co/TheDrummer/Cydonia-22B-v1.2) |
|
|
* [DigitalSouls/BlackSheep-DigitalSoul-22B](https://huggingface.co/DigitalSouls/BlackSheep-DigitalSoul-22B) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: crestf411/MS-sunfall-v0.7.0 |
|
|
parameters: |
|
|
weight: 0.35 |
|
|
density: 0.75 |
|
|
- model: allura-org/MS-Meadowlark-22B |
|
|
parameters: |
|
|
weight: 0.25 |
|
|
density: 0.60 |
|
|
- model: TheDrummer/Cydonia-22B-v1.3 |
|
|
parameters: |
|
|
weight: 0.125 |
|
|
density: 0.55 |
|
|
- model: TheDrummer/Cydonia-22B-v1.2 |
|
|
parameters: |
|
|
weight: 0.125 |
|
|
density: 0.55 |
|
|
- model: anthracite-org/magnum-v4-22b |
|
|
parameters: |
|
|
weight: 0.075 |
|
|
density: 0.45 |
|
|
- model: DigitalSouls/BlackSheep-DigitalSoul-22B |
|
|
parameters: |
|
|
weight: 0.075 |
|
|
density: 0.45 |
|
|
merge_method: della_linear |
|
|
base_model: concedo/Beepo-22B |
|
|
parameters: |
|
|
int8_mask: true |
|
|
normalize: true |
|
|
epsilon: 0.05 |
|
|
lambda: 1.0 |
|
|
dtype: bfloat16 |
|
|
|
|
|
``` |
|
|
|
