Instructions to use squarelike/llama2-ko-medical-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use squarelike/llama2-ko-medical-7b with Transformers:

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

pipe = pipeline("text-generation", model="squarelike/llama2-ko-medical-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("squarelike/llama2-ko-medical-7b")
model = AutoModelForMultimodalLM.from_pretrained("squarelike/llama2-ko-medical-7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use squarelike/llama2-ko-medical-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "squarelike/llama2-ko-medical-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "squarelike/llama2-ko-medical-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/squarelike/llama2-ko-medical-7b

SGLang

How to use squarelike/llama2-ko-medical-7b 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 "squarelike/llama2-ko-medical-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "squarelike/llama2-ko-medical-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "squarelike/llama2-ko-medical-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "squarelike/llama2-ko-medical-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use squarelike/llama2-ko-medical-7b with Docker Model Runner:
```
docker model run hf.co/squarelike/llama2-ko-medical-7b
```

https://github.com/jwj7140/ko-medical-chat

Llama-Ko-Medical-7b

llama2-ko-medical은 llama-2-ko를 기반으로 의료 분야의 한글 raw 데이터를 학습시킨 기반 모델입니다.

학습 데이터

llama2-ko-medical은 약 526MB의 의료 분야 한글 말뭉치로 학습되었습니다. 주요 데이터셋은 다음과 같습니다.

Source	Size (MB)	Link
AIHub 의료, 법률 전문 서적 말뭉치	351.0	aihub.or.kr
하이닥 뉴스 데이터	97.3	hidoc.co.kr
AIHub 전문분야 한영 말뭉치	63.4	aihub.or.kr
질병관리청 국가건강정보포털	8.33	health.kdca.go.kr
보건복지부 국가정신건강정보포털	< 1.0	mentalhealth.go.kr

학습

llama2-ko-medical-7b는 llama-2-ko에서 qlora로 추가 학습되었습니다.

lora_alpha: 16
lora_dropout: 0.01
lora_r: 64
target_modules: q_proj, v_proj
epoch: 3
learning_rate: 3e-4

Downloads last month: 12

Model tree for squarelike/llama2-ko-medical-7b

Adapters

2 models