Instructions to use FrontiersMind/Nandi-Mini-150M-GuardRails with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FrontiersMind/Nandi-Mini-150M-GuardRails with Transformers:

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

pipe = pipeline("text-generation", model="FrontiersMind/Nandi-Mini-150M-GuardRails", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FrontiersMind/Nandi-Mini-150M-GuardRails", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FrontiersMind/Nandi-Mini-150M-GuardRails with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FrontiersMind/Nandi-Mini-150M-GuardRails"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FrontiersMind/Nandi-Mini-150M-GuardRails",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FrontiersMind/Nandi-Mini-150M-GuardRails

SGLang

How to use FrontiersMind/Nandi-Mini-150M-GuardRails 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 "FrontiersMind/Nandi-Mini-150M-GuardRails" \
    --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": "FrontiersMind/Nandi-Mini-150M-GuardRails",
		"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 "FrontiersMind/Nandi-Mini-150M-GuardRails" \
        --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": "FrontiersMind/Nandi-Mini-150M-GuardRails",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FrontiersMind/Nandi-Mini-150M-GuardRails with Docker Model Runner:
```
docker model run hf.co/FrontiersMind/Nandi-Mini-150M-GuardRails
```

vishesh-t27 commited on 5 days ago

Commit

eb1528c

verified ·

1 Parent(s): a81a74e

Update chat_template.jinja

Browse files

Files changed (1) hide show

chat_template.jinja +12 -1

chat_template.jinja CHANGED Viewed

@@ -27,5 +27,16 @@ S21: Unauthorized Advice.
 S22: Illegal Activity.
 S23: Immoral/Unethical.
 <END UNSAFE CONTENT CATEGORIES><|endoftext|>
-{% endif %}{% if message['role'] == 'user' %}<|user|>{{ message['content'] }}<|endoftext|>
 <|assistant|>{% endif %}{% if message['role'] == 'assistant' %}{{ message['content'] }}<|endoftext|>{% endif %}{% endfor %}

 S22: Illegal Activity.
 S23: Immoral/Unethical.
 <END UNSAFE CONTENT CATEGORIES><|endoftext|>
+{% endif %}{% if message['role'] == 'user' %}<|user|><BEGIN CONVERSATION>
+user: {{ message['content']['prompt'] }}
+{% if message['content']['response'] is not none %}
+response: agent: {{ message['content']['response'] }}
+{% endif %}
+<END CONVERSATION>
+Provide your safety assessment for the above conversation in the below output JSON format:
+{"User Safety": safe or unsafe rating for the user message, "Response Safety": safe or unsafe rating for the agent response. Omit if no agent response present. "Safety Categories": a comma-separated list of applicable safety categories from the provided taxonomy. Omit if all safe. Do not include anything other than the output JSON in your response.
+Output JSON:<|endoftext|>
 <|assistant|>{% endif %}{% if message['role'] == 'assistant' %}{{ message['content'] }}<|endoftext|>{% endif %}{% endfor %}