Instructions to use Jarvis1111/MiniGPT4-RobustVLGuard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jarvis1111/MiniGPT4-RobustVLGuard with Transformers:

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

pipe = pipeline("image-text-to-text", model="Jarvis1111/MiniGPT4-RobustVLGuard")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Jarvis1111/MiniGPT4-RobustVLGuard", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Jarvis1111/MiniGPT4-RobustVLGuard with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jarvis1111/MiniGPT4-RobustVLGuard"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jarvis1111/MiniGPT4-RobustVLGuard",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Jarvis1111/MiniGPT4-RobustVLGuard

SGLang

How to use Jarvis1111/MiniGPT4-RobustVLGuard 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 "Jarvis1111/MiniGPT4-RobustVLGuard" \
    --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": "Jarvis1111/MiniGPT4-RobustVLGuard",
		"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 "Jarvis1111/MiniGPT4-RobustVLGuard" \
        --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": "Jarvis1111/MiniGPT4-RobustVLGuard",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Jarvis1111/MiniGPT4-RobustVLGuard with Docker Model Runner:
```
docker model run hf.co/Jarvis1111/MiniGPT4-RobustVLGuard
```

Jarvis1111

nielsr HF Staff commited on Apr 5, 2025

Commit

ce48519

verified ·

1 Parent(s): b23c75a

Add pipeline tag, library name, and project page link (#1)

Browse files

- Add pipeline tag, library name, and project page link (eca599ed17712701a5e6775656b64c6ac6d1e9eb)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -1,7 +1,9 @@
 ---
-license: mit
 datasets:
 - Jarvis1111/RobustVLGuard
 ---
 # 🚀 Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks
@@ -10,6 +12,8 @@ Welcome! This repository hosts the official implementation of our paper, **"Safe
 Paper link: arxiv.org/abs/2504.01308
 ---
 ## 🌟 What’s New?

 ---
 datasets:
 - Jarvis1111/RobustVLGuard
+license: mit
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 # 🚀 Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks
 Paper link: arxiv.org/abs/2504.01308
+Project page:
 ---
 ## 🌟 What’s New?