Instructions to use Jingbiao/Qwen2-VL-7B-Harm-C-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-C-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-C-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-C-LMM-RGCL", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jingbiao/Qwen2-VL-7B-Harm-C-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-C-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-C-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-C-LMM-RGCL

SGLang

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

Improve model card: add pipeline_tag, library_name, license, and paper details

by nielsr HF Staff - opened Sep 13, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+42

-149

nielsr

Sep 13, 2025

This PR significantly improves the model card for the model presented in Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection.

Key changes include:

Updated library_name to transformers: This ensures the "How to use" widget properly displays a transformers code snippet, as the model is compatible with transformers for loading and inference of its PEFT adapters.
Added pipeline_tag: image-text-to-text: This makes the model discoverable under the appropriate task category on the Hugging Face Hub, reflecting its multimodal input and text output capabilities.
Added license: cc-by-4.0: Provides clear licensing information.
Added language: en and relevant tags: Enhances model discoverability.
Populated model card content: The model card now includes the paper title, Hugging Face paper link, the abstract as a detailed model description, and filled-out sections for model details, uses, biases, training, and evaluation, providing comprehensive information about the model.
Added BibTeX citations: The provided BibTeX entries for the associated papers are now correctly placed in the "Citation" section.

Please review and merge this PR if everything looks good.

Improve model card: add pipeline_tag, library_name, license, and paper detailse8b1ad69

Jingbiao changed pull request status to merged Sep 13, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment