metadata
library_name: peft
base_model: EleutherAI/polyglot-ko-5.8b
ChaeMs/KoRani-5.8b
The korean language model finetuned from EleutherAI's polyglot-ko-5.8b, using QLoRA method.
It trained about 100k instruction data.
Instruction data was made using "네이버 지식인" and ShareGPT data.
Model Description
- Developed by: Chae Minsu
- Model type: Text Generation
- Language(s) (NLP): Korean
- Finetuned from model: EleutherAI/polyglot-ko-5.8b
- Training Data: 네이버 지식인 data made by beomi, ShareGPT data made by junelee