DataVortexS-10.7B-dpo-v1.3

Our Team

Research & Engineering	Product Management
Kwangseok Yang	Seunghyun Choi
Jeongwon Choi	Hyoseok Choi

Model Details

Base Model

yanolja/KoSOLAR-10.7B-v0.2

Trained On

• OS: Ubuntu 22.04
• GPU: H100 80GB 4ea
• transformers: v4.36.2

Instruction format

It follows ChatML format.

E.g.

text = """\
<|im_start|>system
당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.<|im_end|>
<|im_start|>user
대한민국의 수도는 어디야?<|im_end|>
<|im_start|>assistant
대한민국의 수도는 서울입니다.<|im_end|>
<|im_start|>user
서울 인구는 총 몇 명이야?<|im_end|>
<|im_start|>assistant
"""

Model Benchmark

Ko LM Eval Harness

Task	0-shot	5-shot	10-shot	50-shot
kobest_boolq	0.91154	0.927338	0.92373	0.653224
kobest_copa	0.747317	0.826961	0.842943	0.860989
kobest_hellaswag	0.445855	0.459065	0.462306	0.4721
kobest_sentineg	0.483219	0.95466	0.964734	0.972292
Average	0.646983	0.792006	0.798428	0.739651

Ko-LLM-Leaderboard

Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
57.65	52.99	64.8	54.86	53.87	61.75

Implementation Code

This model contains the chat_template instruction format.
You can use the code below.

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.3")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.3")

messages = [
    {"role": "system", "content": "당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다."},
    {"role": "user", "content": "대한민국의 수도는 어디야?"},
    {"role": "assistant", "content": "대한민국의 수도는 서울입니다."},
    {"role": "user", "content": "서울 인구는 총 몇 명이야?"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

License

This model is licensed under the cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.