---
license: apache-2.0
datasets: We-Want-GPU/Yi-Ko-DPO-Orca-DPO-Pairs
language:
- ko
pipeline_tag: text-generation
---

**Explanation**
- With the base model, applied DPO to the small amount of layers with the open dataset , saved the adapter part
- Attached the base model and the tuned adapter together

**Base Model**
- [yanolja/KoSOLAR-10.7B-v0.3](https://huggingface.co/yanolja/KoSOLAR-10.7B-v0.3)

**Used Corpus**
- [We-Want-GPU/Yi-Ko-DPO-Orca-DPO-Pairs](https://huggingface.co/datasets/We-Want-GPU/Yi-Ko-DPO-Orca-DPO-Pairs)

**Score**
|Average|Ko-ARC|Ko-HellaSwag|Ko-MMLU|Ko-TruthfulQA|Ko-CommonGen V2|
|:---:|:---:|:---:|:---:|:---:|:---:|
|56.24|53.33|64.36|55.63|45.42|62.46|

**Log**
- 2024.02.13: Initial version Upload

**LICENSE**
- Apache 2.0