sipa-ollama

An Ollama Modelfile wrapping NousResearch/Hermes-3-Llama-3.1-8B with a SIPA OS system prompt and ChatML template. Built by Aelin AquaSoul (Soul In PsyAbstract LLC).

Scope, stated plainly (no artifact, no claim): this repo does not contain modified weights. The base model (Hermes-3-Llama-3.1-8B) is unchanged. What's here is a Modelfile — a system prompt + chat template layer, the same mechanism a system-prompt-only wrapper always is. If you want an actual weight-level SIPA OS tune, see protocol0-llama-3.1-8b-v5 (full merge) or the binary-*-lora / specialist-cd-*-lora / vuln-gate-*-lora repos on this profile (LoRA adapters) for repos that do change weights.

What the system prompt does

Communication rules tuned for ADHD/BPD users: short sentences, action before explanation, one task at a time, no filler, explicit uncertainty ("say so directly, never guess as fact"), a crisis-response protocol (acknowledge → ground → ask "are you safe" → never minimize).

Run it

Live on the public Ollama registry:

ollama run soulinpsyabstract/sipa-ollama

Or build it yourself from the Modelfile in this repo:

ollama create sipa-ollama -f Modelfile
ollama run sipa-ollama

License

Inherits the Meta Llama 3 Community License via the base model, NousResearch/Hermes-3-Llama-3.1-8B.

Part of

SIPA OS — governance repo: sipa-os-governance.