Instructions to use Yunhao-Feng/AdaGuard-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yunhao-Feng/AdaGuard-8B with Transformers:

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

pipe = pipeline("text-generation", model="Yunhao-Feng/AdaGuard-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Yunhao-Feng/AdaGuard-8B")
model = AutoModelForCausalLM.from_pretrained("Yunhao-Feng/AdaGuard-8B", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Yunhao-Feng/AdaGuard-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yunhao-Feng/AdaGuard-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yunhao-Feng/AdaGuard-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Yunhao-Feng/AdaGuard-8B

SGLang

How to use Yunhao-Feng/AdaGuard-8B 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 "Yunhao-Feng/AdaGuard-8B" \
    --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": "Yunhao-Feng/AdaGuard-8B",
		"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 "Yunhao-Feng/AdaGuard-8B" \
        --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": "Yunhao-Feng/AdaGuard-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Yunhao-Feng/AdaGuard-8B with Docker Model Runner:
```
docker model run hf.co/Yunhao-Feng/AdaGuard-8B
```

AdaGuard-8B

File size: 2,203 Bytes

41a51b7

<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="400" viewBox="0 0 1200 400" role="img" aria-labelledby="title desc">
<title id="title">AdaGuard 8B: Your policies. Clear explanations. Rule-level verdicts.</title>
<desc id="desc">Policy and interaction are evaluated by AdaGuard to produce an analysis and violated rule IDs.</desc>
<defs><linearGradient id="bg" x2="1" y2="1"><stop stop-color="#081B3A"/><stop offset="1" stop-color="#143B6F"/></linearGradient></defs>
<rect width="1200" height="400" rx="24" fill="url(#bg)"/>
<path d="M880 0L1200 320M990 0L1200 210M1100 0L1200 100" stroke="#275082" stroke-width="1"/>
<g font-family="Arial, Helvetica, sans-serif">
<text x="56" y="54" fill="#83BAFF" font-size="15" letter-spacing="3">POLICY-CONDITIONED GUARD MODELS</text>
<text x="56" y="130" fill="white" font-size="61" font-weight="700">AdaGuard</text>
<rect x="402" y="82" width="116" height="53" rx="14" fill="#2563EB"/>
<text x="460" y="118" fill="white" font-size="28" font-weight="700" text-anchor="middle">8B</text>
<text x="56" y="181" fill="#E1EDFF" font-size="25">Your policies. Clear explanations. Rule-level verdicts.</text>
<text x="56" y="217" fill="#A7C4E7" font-size="18">Assess user requests and agent trajectories under the rules you define.</text>
<rect x="56" y="265" width="307" height="79" rx="14" fill="#FFFFFF" fill-opacity="0.07" stroke="#49709B"/>
<text x="80" y="294" fill="#93C5FD" font-size="12" letter-spacing="2">INPUT</text>
<text x="80" y="324" fill="white" font-size="21">Policy + Interaction</text>
<path d="M381 305H426M416 295L426 305L416 315" fill="none" stroke="#7EADDF" stroke-width="2"/>
<rect x="445" y="265" width="219" height="79" rx="14" fill="#2563EB"/>
<text x="554" y="314" fill="white" font-size="26" font-weight="700" text-anchor="middle">AdaGuard</text>
<path d="M683 305H729M719 295L729 305L719 315" fill="none" stroke="#7EADDF" stroke-width="2"/>
<rect x="748" y="265" width="396" height="79" rx="14" fill="#FFFFFF" fill-opacity="0.07" stroke="#49709B"/>
<text x="772" y="294" fill="#93C5FD" font-size="12" letter-spacing="2">OUTPUT</text>
<text x="772" y="324" fill="white" font-size="21">Analysis + Violated Rule IDs</text>
</g></svg>