Instructions to use DSAiLab/SHDS-Fin-Thx-7B-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DSAiLab/SHDS-Fin-Thx-7B-v0.3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="DSAiLab/SHDS-Fin-Thx-7B-v0.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DSAiLab/SHDS-Fin-Thx-7B-v0.3")
model = AutoModelForCausalLM.from_pretrained("DSAiLab/SHDS-Fin-Thx-7B-v0.3", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DSAiLab/SHDS-Fin-Thx-7B-v0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DSAiLab/SHDS-Fin-Thx-7B-v0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DSAiLab/SHDS-Fin-Thx-7B-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DSAiLab/SHDS-Fin-Thx-7B-v0.3

SGLang

How to use DSAiLab/SHDS-Fin-Thx-7B-v0.3 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "DSAiLab/SHDS-Fin-Thx-7B-v0.3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DSAiLab/SHDS-Fin-Thx-7B-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "DSAiLab/SHDS-Fin-Thx-7B-v0.3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DSAiLab/SHDS-Fin-Thx-7B-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DSAiLab/SHDS-Fin-Thx-7B-v0.3 with Docker Model Runner:
```
docker model run hf.co/DSAiLab/SHDS-Fin-Thx-7B-v0.3
```

SHDS-Fin-Thx-7B-v0.3

DSAiLab/SHDS-Fin-Thx-7B-v0.3는 Mistral 7B 모델을 백본으로 하여, 한국어 금융 데이터셋을 기반으로 특화 학습된 도메인 모델입니다.

이 모델은 SFT(Supervised Fine-Tuning)와 DPO(Direct Preference Optimization)를 함께 적용하여, 금융 분야에서의 정확도와 응답 일관성을 모두 향상시켰습니다.

Model Summary

Base Model: Mistral-7B
Parameter Count: 7B
Language: Korean (특히 금융/경제 특화)
Training Method:
- SFT: 수집된 고품질 한국 금융 질의응답 데이터 기반 지도 학습
- DPO: 사용자 선호 기반 응답 최적화 (Reward 모델 미사용, Preference-based)

특징

금융 전문화: 보험, 증권, 대출, 투자, 세금 등 한국 금융 영역의 전문 질의응답에 특화
대화형 응답 품질 향상: DPO를 통해 사용자의 선호도에 맞춘 자연스럽고 신뢰도 높은 응답 생성
실사용에 적합: 한국 금융 어플리케이션 및 챗봇 시스템에 바로 적용 가능

지원 프레임워크

HuggingFace Transformers, vLLM, SGLang

Downloads last month: 7