Instructions to use jun47/llava-7b-skin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jun47/llava-7b-skin with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("llava-hf/llava-1.5-7b-hf")
model = PeftModel.from_pretrained(base_model, "jun47/llava-7b-skin")

Transformers

How to use jun47/llava-7b-skin with Transformers:

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

pipe = pipeline("text-generation", model="jun47/llava-7b-skin")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jun47/llava-7b-skin", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jun47/llava-7b-skin with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jun47/llava-7b-skin"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jun47/llava-7b-skin",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jun47/llava-7b-skin

SGLang

How to use jun47/llava-7b-skin 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 "jun47/llava-7b-skin" \
    --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": "jun47/llava-7b-skin",
		"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 "jun47/llava-7b-skin" \
        --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": "jun47/llava-7b-skin",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jun47/llava-7b-skin with Docker Model Runner:
```
docker model run hf.co/jun47/llava-7b-skin
```

LLaVA-1.5-7B Skin Disease Fine-tuned Model (LoRA)

Model Description

이 모델은 llava-hf/llava-1.5-7b-hf 베이스 모델을 기반으로 파인튜닝된 LoRA 어댑터입니다. 안면 피부 질환을 진단하고, 관련 케어 가이드를 제공하는 데 특화되어 있습니다. 기존 범용 모델이 동양인(한국인) 피부 임상 데이터 학습이 부족해 발생하는 오진율과 할루시네이션(임의 처방)을 해결하고자 개발되었습니다.

Base Model: llava-hf/llava-1.5-7b-hf
Finetuning Method: 8-bit QLoRA & RAFT (Retrieval-Augmented Fine-Tuning)
Primary Use Case: 안면 피부 질환 추론 및 다중 턴(Multi-turn) 질의응답 (자가 진단 챗봇)

Training Details

Training Data: AI Hub의 '안면부 피부질환 이미지 합성 데이터' 9,600장을 기반으로, 이미지 당 4개의 단일 턴 질의응답을 하나의 대화 세션으로 묶는 멀티턴 세션 체이닝(Multi-turn Session Chaining) 기법을 적용하여 38,400 Turn 대화셋(QA쌍)으로 가공했습니다.
Results: 피부 질환 진단 Accuracy 약 60% 향상 (0.093 ➔ 0.148), Macro F1-Score 약 65% 향상 (0.126 ➔ 0.208). 반복 생성 루프(Repetition Loop) 버그를 데이터 전처리 레벨에서 원천 해결했습니다.

How to Get Started with the Model

이 모델은 전체 모델이 아닌 LoRA 어댑터(가중치) 입니다. 사용하시려면 peft 라이브러리를 통해 베이스 모델에 어댑터를 로드해야 합니다.

from transformers import AutoProcessor, LlavaForConditionalGeneration
from peft import PeftModel
import torch

# 1. Load Base Model & Processor
base_model_id = "llava-hf/llava-1.5-7b-hf"
processor = AutoProcessor.from_pretrained(base_model_id)
base_model = LlavaForConditionalGeneration.from_pretrained(
    base_model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

# 2. Load LoRA Adapter
adapter_id = "jun47/llava-7b-skin"
model = PeftModel.from_pretrained(base_model, adapter_id)

Downloads last month: 60

Model tree for jun47/llava-7b-skin

Base model

llava-hf/llava-1.5-7b-hf

Adapter

(152)

this model