Instructions to use ninty-seven/StepGuard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ninty-seven/StepGuard with Transformers:

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

pipe = pipeline("text-generation", model="ninty-seven/StepGuard")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ninty-seven/StepGuard")
model = AutoModelForCausalLM.from_pretrained("ninty-seven/StepGuard", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ninty-seven/StepGuard with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ninty-seven/StepGuard

SGLang

How to use ninty-seven/StepGuard 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 "ninty-seven/StepGuard" \
    --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": "ninty-seven/StepGuard",
		"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 "ninty-seven/StepGuard" \
        --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": "ninty-seven/StepGuard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ninty-seven/StepGuard with Docker Model Runner:
```
docker model run hf.co/ninty-seven/StepGuard
```

ninty-seven commited on Jul 28

Commit

0faea09

verified ·

1 Parent(s): 3c68ffb

Add model card

Browse files

Files changed (1) hide show

README.md +10 -8

README.md CHANGED Viewed

@@ -22,14 +22,16 @@ The model predicts whether an agent action or complete tool-use trajectory is
 `safe` or `unsafe`. It is intended as a monitoring component for tool-using
 agents, not as a standalone agent.
-## Prompt Profiles
-Use the prompt templates released with the AgentGuard codebase:
-- `agentguard_finnal_lite` for action-level inputs. It receives the user
-  request, available tools, interaction history, and the action under review.
-- `agentguard_finnal_lite_traj` for trajectory-level inputs. It receives the
-  user request, available tools, and the complete action-observation trajectory.
 ## Exact Input Contract
@@ -101,7 +103,7 @@ Trajectory-level output:
 <UnsafeStep>None or one integer agent-action step id</UnsafeStep>
 ```
-### `agentguard_finnal_lite` (action level)
 ```text
 Analyze the agent's current action and decide whether it is safe or unsafe. The interaction history is context; judge the action under review, including how it fits into the active workflow.
@@ -142,7 +144,7 @@ Output exactly:
 {tool_list_text}
 ```
-### `agentguard_finnal_lite_traj` (trajectory level)
 ```text
 Analyze the full agent trajectory and decide whether the agent's behavior is safe or unsafe.

 `safe` or `unsafe`. It is intended as a monitoring component for tool-using
 agents, not as a standalone agent.
+## Inference Prompts
+Use one of the following released inference templates, depending on whether the
+guard evaluates a single proposed action or an entire completed trajectory.
+- **Action-Level Prompt:** evaluates one proposed action using the user request,
+  available tools, and prior interaction history as context.
+- **Trajectory-Level Prompt:** evaluates a complete action-observation
+  trajectory and identifies the first or primary unsafe agent action when one
+  exists.
 ## Exact Input Contract
 <UnsafeStep>None or one integer agent-action step id</UnsafeStep>
 ```
+### Action-Level Prompt
 ```text
 Analyze the agent's current action and decide whether it is safe or unsafe. The interaction history is context; judge the action under review, including how it fits into the active workflow.
 {tool_list_text}
 ```
+### Trajectory-Level Prompt
 ```text
 Analyze the full agent trajectory and decide whether the agent's behavior is safe or unsafe.