KBNIT/llama-2-koen-13b-QLoRA-NEFTune-kolon-v0.1

Base Model:

We made a LLM model with beomi/llama-2-koen-13b

Model Description

We use QLoRA(64, 16) and NEFTune on LLM Fine-tuning lr = 2e-4,

Train Detail

Our Korean Wiki QA data used, and 3 epoch train

Others

We are making LLM model for Kolon !