Instructions to use Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL with Transformers:

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

pipe = pipeline("image-text-to-text", model="Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL

SGLang

How to use Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL 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 "Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL" \
    --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": "Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL" \
        --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": "Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL with Docker Model Runner:
```
docker model run hf.co/Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL
```

Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection

This repository contains the RA-HMD model presented in the paper Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection.

Model Details

Model Description

RA-HMD proposes a robust adaptation framework for hateful meme detection that enhances in-domain accuracy and cross-domain generalization while preserving the general vision-language capabilities of LMMs. It achieves improved robustness under adversarial attacks compared to SFT models and demonstrates state-of-the-art performance across various meme classification datasets. Additionally, RA-HMD generates higher-quality rationales for explaining hateful content, enhancing model interpretability.

Developed by: Jingbiao Mei, Jinghong Chen, Guangyu Yang, Weizhe Lin, Bill Byrne
Model type: Fine-tuned QWen2-VL-7B-Instruct using PEFT (LoRA)
Language(s) (NLP): English
License: Apache 2.0
Finetuned from model: QWen/QWen2-VL-7B-Instruct

Model Sources

Repository: https://github.com/JingbiaoMei/RGCL
Paper: https://huggingface.co/papers/2502.13061
Project page: https://rgclmm.github.io/

Uses

Direct Use

The model is intended for robust hateful meme detection and generating explanatory rationales.

Out-of-Scope Use

This model is specifically trained for hateful meme detection. Using it for general image captioning or unrelated classification tasks may lead to suboptimal results.

How to Get Started with the Model

Refer to the GitHub repository for detailed installation and usage instructions. The RA-HMD Stage 1 code is released as a submodule in LLaMA-Factory@a88f610.

Citation

If our work helped your research, please kindly cite our paper:

@article{RAHMD2025Mei,
  title={Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection},
  url={http://arxiv.org/abs/2502.13061},
  DOI={10.48550/arXiv.2502.13061},
  note={arXiv:2502.13061 [cs]},
  number={arXiv.2502.13061},
  publisher={arXiv},
  author={Mei, Jingbiao and Chen, Jinghong and Yang, Guangyu and Lin, Weizhe and Byrne, Bill},
  year={2025},
  month=may
}

Downloads last month: -; Downloads are not tracked for this model. How to track

Collection including Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL

RA-HMD

Collection

5 items • Updated Mar 12

Paper for Jingbiao/Qwen2-VL-7B-Harm-P-LMM-RGCL

Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection

Paper • 2502.13061 • Published Feb 18, 2025 • 1