Instructions to use selorahomes/Selora-AI-LLM-1.7B-ollama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use selorahomes/Selora-AI-LLM-1.7B-ollama 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 selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K
# Run inference directly in the terminal:
llama cli -hf selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K
# Run inference directly in the terminal:
llama cli -hf selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K

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 selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K

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 selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K

Use Docker

docker model run hf.co/selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K

LM Studio
Jan

vLLM

How to use selorahomes/Selora-AI-LLM-1.7B-ollama with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "selorahomes/Selora-AI-LLM-1.7B-ollama"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "selorahomes/Selora-AI-LLM-1.7B-ollama",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K

Ollama
How to use selorahomes/Selora-AI-LLM-1.7B-ollama with Ollama:
```
ollama run hf.co/selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K
```
Unsloth Desktop

How to use selorahomes/Selora-AI-LLM-1.7B-ollama with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use selorahomes/Selora-AI-LLM-1.7B-ollama with Docker Model Runner:
```
docker model run hf.co/selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K
```

Lemonade

How to use selorahomes/Selora-AI-LLM-1.7B-ollama with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K

Run and chat with the model

lemonade run user.Selora-AI-LLM-1.7B-ollama-Q6_K

List all available models

lemonade list

Hermes Agent

How to use selorahomes/Selora-AI-LLM-1.7B-ollama with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use selorahomes/Selora-AI-LLM-1.7B-ollama with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "selorahomes/Selora-AI-LLM-1.7B-ollama:Q6_K" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Selora AI — fused single-model build

Qwen3 1.7B fine-tuned for Home Assistant, with all five Selora specialists (command, automation, answer, clarification, utilities) merged into one model. For runtimes that cannot hot-swap LoRA adapters — Ollama being the common case.

The adapter bundle this is merged from lives in selorahomes/Selora-AI: a shared quantized base plus five separate LoRA adapters, swapped per request. That is the reference deployment and the one the Home Assistant integration uses.

Which one do you want?

	This repo	Selora-AI
Ships	One fused GGUF	Base GGUF + 5 LoRA adapters
Runtime	Ollama, llama.cpp — anything that loads a single GGUF	llama.cpp with `--lora`, vLLM with `--enable-lora`
Picks the response type	The model does, from the router prompt	The caller does, by activating one adapter
Accuracy	Lower on automations	Reference scores in `eval/baselines.json`

Merging trades accuracy for simplicity. Each adapter was trained against its own system prompt; the fused model is driven by a router prompt that asks it to choose a response type first, which is not a shape any adapter was trained on. If you can swap adapters, swap adapters.

Quick start

ollama run hf.co/selorahomes/Selora-AI-ollama:selora-ollama.Q6_K.gguf

The filename tag is deliberate. Hugging Face's Ollama integration selects Q4_K_M when present and otherwise picks a reasonable quant from the repo; naming the file removes the guess.

Or build it yourself from the Modelfile in this repo:

ollama create selora -f Modelfile
ollama run selora

The system, template and params files at the repo root configure the same thing for ollama run hf.co/… directly.

Prompt format

ChatML, with /no_think prefixed to the user turn to suppress Qwen3's reasoning block so the output is bare JSON. Inference must match training byte-for-byte; template in this repo is the authoritative form.

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
/no_think {prompt}<|im_end|>
<|im_start|>assistant

The user turn carries the AVAILABLE ENTITIES list, EXISTING AUTOMATIONS, and — for utilities questions — a RELEVANT DOCS block. The model replies with exactly one JSON object, of whichever of the five types it picked. Context is 4096 tokens.

Generation parameters

Set by params / the Modelfile:

temperature    0.0
repeat_penalty 1.0
repeat_last_n  256
stop           <|im_end|>, <|endoftext|>

repeat_penalty stays at 1.0 on purpose. JSON output is mostly repeated structural tokens, and penalising them degrades schema fidelity.

Files

Artifact	Purpose
`selora-ollama.Q6_K.gguf`	The fused model
`Modelfile`	Ollama recipe (model + router prompt + params)
`system`	Router system prompt
`template`	Go chat template
`params`	Sampler settings
`manifest.json`	Version, checksum, provenance

All five are generated from the models repo — data-pipeline/prompts/router_system_prompt.txt is the source of truth for the system prompt. Don't edit them here; they are overwritten on every release.

Versioning

main is the latest release, and each release is also tagged v<x.y.z>. Versions track the adapter bundle in selorahomes/Selora-AI: the same manifest.json version covers both, because both are built from one conversion run.