Instructions to use achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO with Transformers:

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

pipe = pipeline("image-text-to-text", model="achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO")
model = AutoModelForMultimodalLM.from_pretrained("achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO

SGLang

How to use achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO 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 "achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO" \
    --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": "achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO",
		"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 "achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO" \
        --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": "achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO with Docker Model Runner:
```
docker model run hf.co/achernarwang/SPY_Qwen2-VL-7B-Instruct_DPO
```

SPY_Qwen2-VL-7B-Instruct_DPO

This model is a fine-tuned version of Qwen2-VL-7B, trained on our SPY-Tune dataset using the DPO algorithm.

It serves as one of the finetuning baselines in our ACM Multimedia 2025 BNI Oral paper:

Specify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models

For more details about the dataset, training process, and evaluation metrics, please refer to our GitHub repository: https://github.com/achernarwang/specify-privacy-yourself