Instructions to use hivetrace/HiveTraceGuard-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hivetrace/HiveTraceGuard-Pro with Transformers:

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

pipe = pipeline("text-generation", model="hivetrace/HiveTraceGuard-Pro")
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("hivetrace/HiveTraceGuard-Pro")
model = AutoModelForCausalLM.from_pretrained("hivetrace/HiveTraceGuard-Pro", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hivetrace/HiveTraceGuard-Pro with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hivetrace/HiveTraceGuard-Pro

SGLang

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

Docker Model Runner
How to use hivetrace/HiveTraceGuard-Pro with Docker Model Runner:
```
docker model run hf.co/hivetrace/HiveTraceGuard-Pro
```

nikiduki commited on Aug 19

Commit

be379f3

verified ·

1 Parent(s): 9ea0a0b

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -19,8 +19,7 @@ tags:
 # HiveTraceGuard-Pro
-**HiveTraceGuard-Pro** is a compact Russian-first guardrail built on [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) for fast input and output classification. Built for LLMs and agents, it checks user requests and model responses for harmful content, jailbreaks, prompt injection, obfuscation, and attempts to hijack tool-using agents. The model is stateless and returns exactly one token: `safe` or `unsafe`. Its policy is fixed, so serving runtimes can reuse the shared prefix through KV caching.
 # Quickstart
@@ -76,6 +75,8 @@ print(check([
 ```
 ## Serve
 ### vLLM

 # HiveTraceGuard-Pro
+**HiveTraceGuard-Pro** is a compact Russian-first guardrail built on [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) for fast input and output classification. Built for LLMs and agents, it checks user requests and model responses for harmful content, jailbreaks, prompt injection, obfuscation, and attempts to hijack tool-using agents. The model is stateless and returns exactly one token: `safe` or `unsafe`.
 # Quickstart
 ```
 ## Serve
+Model's policy is fixed, so serving runtimes can reuse the shared prefix through KV caching.
 ### vLLM