Instructions to use SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507")

Transformers

How to use SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507 with Transformers:

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

pipe = pipeline("text-generation", model="SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507

SGLang

How to use SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507 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 "SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507" \
    --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": "SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507",
		"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 "SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507" \
        --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": "SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507 with Docker Model Runner:
```
docker model run hf.co/SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507
```

Fine-Tuning a Model to Detect Prompt Injection

by Ask951169 - opened 14 days ago

Discussion

Ask951169

14 days ago

Hey, I came across your AgentWatcher model for detecting prompt injection in AI agents. That’s an interesting use case. How did you approach creating training examples for attacks hidden inside external content?

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