Yi-Ko-6B-Instruct-v1.0

Model Details

Base Model

beomi/Yi-Ko-6B

Training Dataset

1. kyujinpy/KOR-OpenOrca-Platypus-v3 🙇
2. beomi/KoAlpaca-v1.1a 🙇
3. maywell/ko_wikidata_QA 🙇
4. AIHub MRC 데이터 선별 후 Instruction Format 맞게 변경 후 사용

Benchmark Results

AI-Harness Evaluation

https://github.com/Beomi/ko-lm-evaluation-harness

Model	kobest_boolq	kobest_copa	kobest_hellaswag	kobest_sentineg	korunsmile	pawsx_ko
	Zero-shot
Yi-Ko-6B-Instruct-v1.0	0.6619	0.7794	0.4858	0.4589	0.3520	0.5545
Yi-Ko-6B	0.7070	0.7696	0.5009	0.4044	0.3828	0.5145

Instruction Format

### User:
{instruction}

### Assistant:
{response}

Loading the Model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("wkshin89/Yi-Ko-6B-Instruct-v1.0")
model = AutoModelForCausalLM.from_pretrained(
    "wkshin89/Yi-Ko-6B-Instruct-v1.0",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)