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.