DataVortexS-10.7B-v0.4

Our Team

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

Model Details

Base Model

LDCC/LDCC-SOLAR-10.7B

Trained On

• OS: Ubuntu 20.04
• GPU: H100 80GB 2ea
• transformers: v4.36.2

Dataset

• Edentns/data_go_kr-PublicDoc - private
• Edentns/aihub-TL_unanswerable_output - private
• Edentns/aihub-TL_span_extraction_how_output - private
• Edentns/aihub-TL_multiple_choice_output - private
• Edentns/aihub-TL_text_entailment_output - private
• jojo0217/korean_rlhf_dataset
• kyujinpy/KOR-OpenOrca-Platypus-v3
• beomi/KoAlpaca-v1.1a
• HumanF-MarkrAI/WIKI_QA_Near_dedup

Instruction format

It follows Alpaca format.

E.g.

text = """\
당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.

### Instruction:
대한민국의 수도는 어디야?

### Response:
대한민국의 수도는 서울입니다.

### Instruction:
서울 인구는 총 몇 명이야?
"""

Model Benchmark

Ko LM Eval Harness

Task	0-shot	5-shot	10-shot	50-shot
kobest_boolq	0.389066	0.912924	0.912808	0.906428
kobest_copa	0.744865	0.747742	0.768856	0.785896
kobest_hellaswag	0.455793	0.443909	0.465783	0.472771
kobest_sentineg	0.584156	0.947082	0.962216	0.954657
Average	0.54347	0.76291425	0.77741575	0.779938

Ko-LLM-Leaderboard

Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
54.15	49.4	59.7	54.63	47.5	59.5

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-v0.4")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-v0.4")

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

The model is licensed under the cc-by-nc-sa-4.0 license, which allows others to copy, modify, and share the work non-commercially, as long as they give appropriate credit and distribute any derivative works under the same license.