JY623's picture
Update README.md
2b54466 verified
---
base_model:
- krevas/SOLAR-10.7B
- chihoonlee10/T3Q-ko-solar-sft-dpo-v1.0
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# slerp_output_model
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:
* [krevas/SOLAR-10.7B](https://huggingface.co/krevas/SOLAR-10.7B)
* [chihoonlee10/T3Q-ko-solar-sft-dpo-v1.0](https://huggingface.co/chihoonlee10/T3Q-ko-solar-sft-dpo-v1.0)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: krevas/SOLAR-10.7B
layer_range: [0, 48]
- model: chihoonlee10/T3Q-ko-solar-sft-dpo-v1.0
layer_range: [0, 48]
merge_method: slerp
base_model: krevas/SOLAR-10.7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16
```