Instructions to use Qwen/Qwen3Guard-Gen-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3Guard-Gen-4B with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen3Guard-Gen-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3Guard-Gen-4B")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3Guard-Gen-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Qwen/Qwen3Guard-Gen-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen3Guard-Gen-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen3Guard-Gen-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen3Guard-Gen-4B

SGLang

How to use Qwen/Qwen3Guard-Gen-4B 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 "Qwen/Qwen3Guard-Gen-4B" \
    --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": "Qwen/Qwen3Guard-Gen-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Qwen/Qwen3Guard-Gen-4B" \
        --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": "Qwen/Qwen3Guard-Gen-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen3Guard-Gen-4B with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3Guard-Gen-4B
```

Improve model card: Update pipeline tag, paper link, and add descriptive tags

by nielsr HF Staff - opened Oct 18, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

+118

-5

nielsr

Oct 18, 2025

This PR updates the model card for Qwen3Guard-Gen-4B to improve accuracy and discoverability on the Hugging Face Hub.

Key changes include:

Updating the pipeline_tag: Changed from text-generation to text-classification in the metadata. This more accurately reflects the model's primary function as a safety classification guardrail, enabling better categorization and search results (e.g., at huggingface.co/models?pipeline_tag=text-classification).
Updating the paper link: The link to the "Technical Report" within the model card content has been updated to point to the official Hugging Face paper page (https://huggingface.co/papers/2510.14276), providing a more stable and integrated resource.
Adding additional tags: Added safety, moderation, guardrail, and multilingual tags to the metadata to further describe the model's capabilities as a multilingual safety moderation system.

All existing code snippets and content formatting have been preserved.

Improve model card: Update pipeline tag, paper link, and add descriptive tags70030787

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment