Instructions to use haic-hmgu/dermatology-captioning-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use haic-hmgu/dermatology-captioning-12b with Transformers:

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

pipe = pipeline("image-text-to-text", model="haic-hmgu/dermatology-captioning-12b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("haic-hmgu/dermatology-captioning-12b")
model = AutoModelForMultimodalLM.from_pretrained("haic-hmgu/dermatology-captioning-12b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use haic-hmgu/dermatology-captioning-12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "haic-hmgu/dermatology-captioning-12b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "haic-hmgu/dermatology-captioning-12b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/haic-hmgu/dermatology-captioning-12b

SGLang

How to use haic-hmgu/dermatology-captioning-12b 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 "haic-hmgu/dermatology-captioning-12b" \
    --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": "haic-hmgu/dermatology-captioning-12b",
		"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 "haic-hmgu/dermatology-captioning-12b" \
        --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": "haic-hmgu/dermatology-captioning-12b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use haic-hmgu/dermatology-captioning-12b with Docker Model Runner:
```
docker model run hf.co/haic-hmgu/dermatology-captioning-12b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Licence

This model is a Gemma Model Derivative and is distributed under the Gemma Terms of Use, including the Prohibited Use Policy, which apply to you as a recipient. See the LICENSE file in this repository for the full agreement.

Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms

Citation

Paper in preparation; citation will be added here on publication.

Downloads last month: 15

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for haic-hmgu/dermatology-captioning-12b

Base model

google/gemma-3-12b-pt

Finetuned

(118)

this model

Quantizations

1 model