|
--- |
|
base_model: |
|
- intervitens/mini-magnum-12b-v1.1 |
|
- grimjim/mistralai-Mistral-Nemo-Instruct-2407 |
|
- Gryphe/Pantheon-RP-1.6.1-12b-Nemo |
|
- anthracite-org/magnum-v4-12b |
|
- anthracite-org/magnum-v2.5-12b-kto |
|
- TheDrummer/Rocinante-12B-v1.1 |
|
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 [grimjim/mistralai-Mistral-Nemo-Instruct-2407](https://huggingface.co/grimjim/mistralai-Mistral-Nemo-Instruct-2407) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [intervitens/mini-magnum-12b-v1.1](https://huggingface.co/intervitens/mini-magnum-12b-v1.1) |
|
* [Gryphe/Pantheon-RP-1.6.1-12b-Nemo](https://huggingface.co/Gryphe/Pantheon-RP-1.6.1-12b-Nemo) |
|
* [anthracite-org/magnum-v4-12b](https://huggingface.co/anthracite-org/magnum-v4-12b) |
|
* [anthracite-org/magnum-v2.5-12b-kto](https://huggingface.co/anthracite-org/magnum-v2.5-12b-kto) |
|
* [TheDrummer/Rocinante-12B-v1.1](https://huggingface.co/TheDrummer/Rocinante-12B-v1.1) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: Gryphe/Pantheon-RP-1.6.1-12b-Nemo |
|
parameters: |
|
weight: 0.35 |
|
density: 0.9 |
|
- model: TheDrummer/Rocinante-12B-v1.1 |
|
parameters: |
|
weight: 0.25 |
|
density: 0.8 |
|
- model: anthracite-org/magnum-v4-12b |
|
parameters: |
|
weight: 0.15 |
|
density: 0.7 |
|
- model: intervitens/mini-magnum-12b-v1.1 |
|
parameters: |
|
weight: 0.15 |
|
density: 0.6 |
|
- model: anthracite-org/magnum-v2.5-12b-kto |
|
parameters: |
|
weight: 0.10 |
|
density: 0.5 |
|
merge_method: della_linear |
|
base_model: grimjim/mistralai-Mistral-Nemo-Instruct-2407 |
|
parameters: |
|
epsilon: 0.01 |
|
lambda: 0.8 |
|
dtype: bfloat16 |
|
tokenizer_source: base |
|
``` |
|
|
