|
--- |
|
license: cc-by-nc-sa-4.0 |
|
tags: |
|
- 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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [chihoonlee10/T3Q-ko-solar-dpo-v5.0](https://huggingface.co/chihoonlee10/T3Q-ko-solar-dpo-v5.0) |
|
* [krevas/SOLAR-10.7B](https://huggingface.co/krevas/SOLAR-10.7B) |
|
* [hyeogi/SOLAR-10.7B-v1.6](https://huggingface.co/hyeogi/SOLAR-10.7B-v1.6) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: chihoonlee10/T3Q-ko-solar-dpo-v5.0 |
|
parameters: |
|
density: [1, 0.7, 0.1] # density gradient |
|
weight: 1.0 |
|
- model: hyeogi/SOLAR-10.7B-v1.6 |
|
parameters: |
|
density: 0.5 |
|
weight: [0, 0.3, 0.7, 1] # weight gradient |
|
- model: krevas/SOLAR-10.7B |
|
parameters: |
|
density: 0.33 |
|
weight: |
|
- filter: mlp |
|
value: 0.5 |
|
- value: 0 |
|
merge_method: ties |
|
base_model: upstage/SOLAR-10.7B-v1.0 |
|
parameters: |
|
normalize: true |
|
int8_mask: true |
|
dtype: float16 |
|
|
|
``` |
