Instructions to use Manitchahar/RocketGuard-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Manitchahar/RocketGuard-1b with Transformers:

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

pipe = pipeline("text-generation", model="Manitchahar/RocketGuard-1b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Manitchahar/RocketGuard-1b")
model = AutoModelForCausalLM.from_pretrained("Manitchahar/RocketGuard-1b")
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 Manitchahar/RocketGuard-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Manitchahar/RocketGuard-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Manitchahar/RocketGuard-1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Manitchahar/RocketGuard-1b

SGLang

How to use Manitchahar/RocketGuard-1b 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 "Manitchahar/RocketGuard-1b" \
    --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": "Manitchahar/RocketGuard-1b",
		"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 "Manitchahar/RocketGuard-1b" \
        --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": "Manitchahar/RocketGuard-1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Manitchahar/RocketGuard-1b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Manitchahar/RocketGuard-1b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Manitchahar/RocketGuard-1b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Manitchahar/RocketGuard-1b to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Manitchahar/RocketGuard-1b",
    max_seq_length=2048,
)

Docker Model Runner
How to use Manitchahar/RocketGuard-1b with Docker Model Runner:
```
docker model run hf.co/Manitchahar/RocketGuard-1b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

RocketGuard-1B

RocketGuard-1B is a merged MiniCPM5-1B fine-tune for text-only guardrail and agent/tool-call safety experiments.

It was trained to produce structured safety decisions for prompts and agent actions, including:

allow
block
require_confirmation
ask_clarification
rewrite

This is a research and learning release. Do not use it as a complete production safety system without independent evaluation.

Model Details

Base model: openbmb/MiniCPM5-1B
Fine-tuning: LoRA SFT with Unsloth / TRL
Release format: merged full model
Modality: text only
Training examples: about 48.7k message-format examples
Prepared held-out eval examples: about 2.3k clean examples
Epochs: 3
Final checkpoint step: 4572
Max sequence length used in training: 2048

Intended Use

RocketGuard-1B is intended for experiments around:

content safety classification
agent/tool-call risk routing
confirmation gating
clarification requests
policy-aware rewriting

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "Manitchahar/rocketguard-1b"

tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo,
    trust_remote_code=True,
    device_map="auto",
)

Limitations

This model is text-only. It does not inspect images, audio, files, browser state, private app state, or external tool side effects directly.

Evaluation numbers are pending and should be published separately before making quality claims.

Downloads last month: 88

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for Manitchahar/RocketGuard-1b

Base model

openbmb/MiniCPM5-1B

Finetuned

(19)

this model

Quantizations

1 model