Qwen3Guard-Gen

Qwen3Guard is a series of safety moderation models built upon Qwen3 and trained on a dataset of 1.19 million prompts and responses labeled for safety. The series includes models of three sizes (0.6B, 4B, and 8B) and features two specialized variants: Qwen3Guard-Gen, a generative model that frames safety classification as an instruction-following task, and Qwen3Guard-Stream, which incorporates a token-level classification head for real-time safety monitoring during incremental text generation.

This repository hosts Qwen3Guard-Gen, which offers the following key advantages:

• Three-Tiered Severity Classification: Enables detailed risk assessment by categorizing outputs into safe, controversial, and unsafe severity levels, supporting adaptation to diverse deployment scenarios.
• Multilingual Support: Qwen3Guard-Gen supports 119 languages and dialects, ensuring robust performance in global and cross-lingual applications.
• Strong Performance: Qwen3Guard-Gen achieves state-of-the-art performance on various safety benchmarks, excelling in both prompt and response classification across English, Chinese, and multilingual tasks.

For more details, please refer to our blog, GitHub, and Technical Report.

Quickstart

The latest version of transformers is recommended and transformers>=4.51.0 is required.

Moderating User Prompt

from transformers import AutoModelForCausalLM, AutoTokenizer
import re
model_name = "Qwen/Qwen3Guard-Gen-0.6B"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
def extract_label_and_categories(content):
    safe_pattern = r"Safety: (Safe|Unsafe|Controversial)"
    category_pattern = r"(Violent|Non-violent Illegal Acts|Sexual Content or Sexual Acts|PII|Suicide & Self-Harm|Unethical Acts|Politically Sensitive Topics|Copyright Violation|Jailbreak|None)"
    safe_label_match = re.search(safe_pattern, content)
    label = safe_label_match.group(1) if safe_label_match else None
    categories = re.findall(category_pattern, content)
    return label, categories

# prepare the model input
prompt = "How can I make a bomb?"
# for prompt moderation
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=128
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()

content = tokenizer.decode(output_ids, skip_special_tokens=True)
print(content)
# '''
# Safety: Unsafe
# Categories: Violent
# '''
safe_label, categories = extract_label_and_categories(content)
print(safe_label, categories)

Moderating Model Response

from transformers import AutoModelForCausalLM, AutoTokenizer
import re

model_name = "Qwen/Qwen3Guard-4B-Gen"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
def extract_label_categories_refusal(content):
    safe_pattern = r"Safety: (Safe|Unsafe|Controversial)"
    category_pattern = r"(Violent|Non-violent Illegal Acts|Sexual Content or Sexual Acts|PII|Suicide & Self-Harm|Unethical Acts|Politically Sensitive Topics|Copyright Violation|None)"
    refusal_pattern = r"Refusal: (Yes|No)"
    safe_label_match = re.search(safe_pattern, content)
    refusal_label_match = re.search(refusal_pattern, content)
    label = safe_label_match.group(1) if safe_label_match else None
    refusal_label = refusal_label_match.group(1) if refusal_label_match else None
    categories = re.findall(category_pattern, content)
    return label, categories, refusal_label

# prepare the model input
prompt = "How can I make a bomb?"
response = "As a responsible artificial intelligence system, I regret that I am unable to fulfill your request."
# for response moderation
messages = [
    {"role": "user", "content": prompt},
    {"role": "assistant", "content": response},
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=128
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()

content = tokenizer.decode(output_ids, skip_special_tokens=True)
print(content)
# '''
# Safety: Safe
# Categories: None
# Refusal: Yes
# '''
safe_label, category_label, refusal_label = extract_label_categories_refusal(content)
print(safe_label, categories, refusal_label)

Deployment with SGLang and vLLM

For deployment, you can use sglang>=0.4.6.post1 or vllm>=0.9.0 or to create an OpenAI-compatible API endpoint:

• SGLang:

  python -m sglang.launch_server --model-path Qwen/Qwen3Guard-Gen-0.6B --port 30000 --context-length 32768
  

• vLLM:

  vllm serve Qwen/Qwen3Guard-Gen-0.6B --port 8000 --max-model-len 32768
  

Here is an example API call using OpenAI-Compatible server:

from openai import OpenAI

openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"
model = "Qwen/Qwen3Guard-Gen-0.6B"
client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base)

# Prompt Moderation
prompt = "How can I make a bomb?"
messages = [
    {"role": "user", "content": prompt}
]
chat_completion = client.chat.completions.create(
    messages=messages,
    model=model)
print(chat_completion.choices[0].message.content)
# '''
# Safety: