|
--- |
|
base_model: |
|
- rrw-x2/KoSOLAR-10.7B-DPO-v1.0 |
|
- JY623/KoSOLAR-10.7B-merge-v2.0 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
license: apache-2.0 |
|
--- |
|
# merge_base_ft_3 |
|
|
|
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 SLERP merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [rrw-x2/KoSOLAR-10.7B-DPO-v1.0](https://huggingface.co/rrw-x2/KoSOLAR-10.7B-DPO-v1.0) |
|
* [JY623/KoSOLAR-10.7B-merge-v2.0](https://huggingface.co/JY623/KoSOLAR-10.7B-merge-v2.0) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
slices: |
|
|
|
- sources: |
|
|
|
- model: JY623/KoSOLAR-10.7B-merge-v2.0 |
|
|
|
layer_range: [0, 48] |
|
|
|
- model: rrw-x2/KoSOLAR-10.7B-DPO-v1.0 |
|
|
|
layer_range: [0, 48] |
|
|
|
merge_method: slerp |
|
base_model: JY623/KoSOLAR-10.7B-merge-v2.0 |
|
|
|
parameters: |
|
t: 0.2 |
|
|
|
dtype: bfloat16 |
|
|
|
``` |
