README.md

metadata

tags:
  - text-generation
license: cc-by-nc-sa-4.0
language:
  - ko
base_model: megastudy/M-SOLAR-10.7B-v1.3
pipeline_tag: text-generation

DataVortexS-10.7B-v1.0

Our Team

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

Model Details

Base Model

megastudy/M-SOLAR-10.7B-v1.3

Trained On

• OS: Ubuntu 20.04
• GPU: H100 80GB 4ea
• transformers: v4.36.2

Instruction format

It follows Alpaca format.

E.g.

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

### User:
대한민국의 수도는 어디야?

### Assistant:
대한민국의 수도는 서울입니다.

### User:
서울 인구는 총 몇 명이야?
"""

Model Benchmark

Ko LM Eval Harness

Task	0-shot	5-shot	10-shot	50-shot
kobest_boolq	0.334282	0.334282	0.334282	0.769923
kobest_copa	0.480501	0.475746	0.46338	0.475528
kobest_hellaswag	0.225818	0.240596	0.234316	0.449779
kobest_sentineg	0.33165	0.386189	0.366913	0.360296
Average	0.34306275	0.35920325	0.34972275	0.5138815

Ko-LLM-Leaderboard

Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
40.75	49.06	25.66	53.63	45.76	29.63

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-v1.0")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-v1.0")

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.