Instructions to use meta-llama/Llama-Guard-3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-Guard-3-8B with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Llama-Guard-3-8B")
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("meta-llama/Llama-Guard-3-8B")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-Guard-3-8B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/Llama-Guard-3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Llama-Guard-3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-Guard-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-Guard-3-8B

SGLang

How to use meta-llama/Llama-Guard-3-8B 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 "meta-llama/Llama-Guard-3-8B" \
    --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": "meta-llama/Llama-Guard-3-8B",
		"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 "meta-llama/Llama-Guard-3-8B" \
        --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": "meta-llama/Llama-Guard-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meta-llama/Llama-Guard-3-8B with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-Guard-3-8B
```

Request for review of rejected access — Cosmos safety dependency (tyb666)

#37

by tyb666 - opened 11 days ago

Discussion

tyb666

11 days ago

Hello Meta Llama team,

My Hugging Face username is tyb666. My access request for meta-llama/Llama-Guard-3-8B was rejected, but the page does not provide a specific reason. Could you please review the decision, or let me know what information needs to be corrected or supplemented?

I am conducting a research experiment on the physical consistency of generated videos: a Blender-created cube falling onto a platform in a synthetic laboratory scene. I am using the official NVIDIA Cosmos-Predict2.5-2B and Cosmos-Predict1-5B-Video2World inference pipelines. Llama Guard is required by their official safety-checking components, which I intend to keep enabled. Access to the Cosmos model repositories and NVIDIA Cosmos-Guardrail1 has already been approved.

If reconsideration is possible, could you please reopen/reset my request or point me to the appropriate private support channel? I can provide any additional application details privately.

Thank you for your time and guidance.

tyb666 changed discussion status to closed 11 days ago

tyb666 changed discussion status to open 11 days ago

RedAndBlack123

10 days ago

bro change location

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