The license is cc-by-nc-4.0.

GAI-LLM/Yi-Ko-6B-dpo-v5

Model Details

Model Developers Donghoon Oh, Hanmin Myung(SK C&C G.AI Eng)

Input Models input text only.

Output Models generate text only.

Model Architecture
Yi-Ko-6B-dpo-v5 is an auto-regressive language model based on the LLaMA2 transformer architecture.

Base Model beomi/Yi-Ko-6B

Training Dataset

• We combined Open Korean Dateset using mixed-strategy with DPO.
• We use A100 GPU 80GB * 8, when training.

Model Benchmark

KO-LLM leaderboard

• Follow up as Open KO-LLM LeaderBoard.

Implementation Code

### GAI-LLM/Yi-Ko-6B-dpo-v5
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "GAI-LLM/Yi-Ko-6B-dpo-v5"
model = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)