|
|
--- |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- ko |
|
|
--- |
|
|
## Model Details |
|
|
|
|
|
**Model Developers** Yunho Mo (momo) |
|
|
|
|
|
**Input** Models input text only. |
|
|
|
|
|
**Output** Models generate text only. |
|
|
|
|
|
**Model Architecture** |
|
|
|
|
|
polyglot-ko-12.8b-Chat-QLoRA-Merge is an auto-regressive language model based on the polyglot-ko-12.8b transformer architecture. |
|
|
|
|
|
**Base Model** |
|
|
[polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) |
|
|
|
|
|
**Training Dataset** |
|
|
|
|
|
I use [KOpen-platypus](https://huggingface.co/datasets/kyujinpy/KOpen-platypus), [ko-lima](https://huggingface.co/datasets/taeshahn/ko-lima), [EverythingLM-data-V2-Ko](https://huggingface.co/datasets/ziozzang/EverythingLM-data-V2-Ko). |
|
|
|
|
|
|
|
|
|
