Instructions to use oggoscaps/rp3-gate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oggoscaps/rp3-gate with Transformers:

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

pipe = pipeline("text-generation", model="oggoscaps/rp3-gate")
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("oggoscaps/rp3-gate")
model = AutoModelForCausalLM.from_pretrained("oggoscaps/rp3-gate", 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

llama.cpp

How to use oggoscaps/rp3-gate with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf oggoscaps/rp3-gate:Q8_0
# Run inference directly in the terminal:
llama cli -hf oggoscaps/rp3-gate:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf oggoscaps/rp3-gate:Q8_0
# Run inference directly in the terminal:
llama cli -hf oggoscaps/rp3-gate:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf oggoscaps/rp3-gate:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf oggoscaps/rp3-gate:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf oggoscaps/rp3-gate:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf oggoscaps/rp3-gate:Q8_0

Use Docker

docker model run hf.co/oggoscaps/rp3-gate:Q8_0

LM Studio
Jan

vLLM

How to use oggoscaps/rp3-gate with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oggoscaps/rp3-gate"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oggoscaps/rp3-gate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/oggoscaps/rp3-gate:Q8_0

SGLang

How to use oggoscaps/rp3-gate 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 "oggoscaps/rp3-gate" \
    --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": "oggoscaps/rp3-gate",
		"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 "oggoscaps/rp3-gate" \
        --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": "oggoscaps/rp3-gate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use oggoscaps/rp3-gate with Ollama:
```
ollama run hf.co/oggoscaps/rp3-gate:Q8_0
```
Unsloth Desktop
Docker Model Runner
How to use oggoscaps/rp3-gate with Docker Model Runner:
```
docker model run hf.co/oggoscaps/rp3-gate:Q8_0
```

Lemonade

How to use oggoscaps/rp3-gate with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull oggoscaps/rp3-gate:Q8_0

Run and chat with the model

lemonade run user.rp3-gate-Q8_0

List all available models

lemonade list

Atomic Chat

rp3-gate

A small gatekeeper. Talk to it and it will tell you where to go next.

This is a fine-tune of google/gemma-3-1b-it (1B parameters, ~2 GB). It runs on an ordinary laptop CPU — no GPU needed.

Run it

Option 1 — Ollama (easiest)

Download rp3-gate-q8_0.gguf from the Files tab, then in the same folder:

ollama create rp3-gate -f Modelfile
ollama run rp3-gate

(The Modelfile is in the Files tab too — put it next to the .gguf.)

Option 2 — Python / transformers

pip install -U transformers torch

from transformers import pipeline

chat = pipeline("text-generation", model="oggoscaps/rp3-gate")
print(chat([{"role": "user", "content": "hello?"}], max_new_tokens=120)[0]["generated_text"][-1]["content"])

Option 3 — llama.cpp

llama-cli -m rp3-gate-q8_0.gguf -cnv

Notes

Gemma is provided under and subject to the Gemma Terms of Use.
Deterministic by default (do_sample=false). Sampling works too; the gatekeeper is stubborn either way.
It will not be talked out of its job. Many have tried.

Downloads last month: 79

Safetensors

Model size

1B params

Tensor type

F32

Model tree for oggoscaps/rp3-gate

Base model

google/gemma-3-1b-pt

Finetuned

google/gemma-3-1b-it

Quantized

(481)

this model