README.md

metadata

license: cc-by-nc-4.0
language:
  - ko
  - en

Base Model:

We made a LLM model with meta-llama/Meta-Llama-3-8B

Model Description

We use QDoRA(256, 64) and lr=1e-5, NEFTune=3

Train Detail

Our changed private data used, and 5 epoch train

Others

We are making LLM model for Kolon !