Instructions to use solidrust/Meta-Llama-Guard-2-8B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/Meta-Llama-Guard-2-8B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/Meta-Llama-Guard-2-8B-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/Meta-Llama-Guard-2-8B-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/Meta-Llama-Guard-2-8B-AWQ")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use solidrust/Meta-Llama-Guard-2-8B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/Meta-Llama-Guard-2-8B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/Meta-Llama-Guard-2-8B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/solidrust/Meta-Llama-Guard-2-8B-AWQ

SGLang

How to use solidrust/Meta-Llama-Guard-2-8B-AWQ 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 "solidrust/Meta-Llama-Guard-2-8B-AWQ" \
    --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": "solidrust/Meta-Llama-Guard-2-8B-AWQ",
		"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 "solidrust/Meta-Llama-Guard-2-8B-AWQ" \
        --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": "solidrust/Meta-Llama-Guard-2-8B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use solidrust/Meta-Llama-Guard-2-8B-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/Meta-Llama-Guard-2-8B-AWQ
```

meta-llama/Meta-Llama-Guard-2-8B AWQ

Model creator: meta-llama
Original model: Meta-Llama-Guard-2-8B

Model Summary

Meta Llama Guard 2 is an 8B parameter Llama 3-based [1] LLM safeguard model. Similar to Llama Guard, it can be used for classifying content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated. Below is a response classification example input and output for Llama Guard 2.

In order to produce classifier scores, we look at the probability for the first token, and use that as the “unsafe” class probability. We can then apply score thresholding to make binary decisions.