README.md

metadata

tags:
  - text-generation
license: cc-by-nc-sa-4.0
language:
  - ko
base_model: hyeogi/SOLAR-10.7B-dpo-v0.1
pipeline_tag: text-generation
datasets:
  - beomi/KoAlpaca-v1.1a
  - Edentns/Worktronics-FAQ

DataVortexS-10.7B-v0.2

Our Team

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

Model Details

Base Model

hyeogi/SOLAR-10.7B-dpo-v0.1

Trained On

• OS: Ubuntu 20.04
• GPU: H100 80GB 1ea
• transformers: v4.36.2

Dataset

• beomi/KoAlpaca-v1.1a
• Edentns/Worktronics-FAQ - private

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	0.501449	0.668845	0.652565	0.655491
kobest_copa	0.635474	0.685637	0.708601	0.725683
kobest_hellaswag	0.417966	0.442942	0.428077	0.425199
kobest_sentineg	0.681941	0.880517	0.921754	0.939528
Average	0.5592075	0.66948525	0.67774925	0.68647525

Ko-LLM-Leaderboard

Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
43.6	38.74	50.74	38.98	44.7	44.86

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-v0.2")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-v0.2")

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.