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

Libraries

How to use selorahomes/Selora-AI with Transformers:

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

pipe = pipeline("text-generation", model="selorahomes/Selora-AI")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("selorahomes/Selora-AI", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use selorahomes/Selora-AI 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:Q6_K
# Run inference directly in the terminal:
llama cli -hf selorahomes/Selora-AI: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:Q6_K
# Run inference directly in the terminal:
llama cli -hf selorahomes/Selora-AI: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:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf selorahomes/Selora-AI: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:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf selorahomes/Selora-AI:Q6_K

Use Docker

docker model run hf.co/selorahomes/Selora-AI:Q6_K

LM Studio
Jan

vLLM

How to use selorahomes/Selora-AI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "selorahomes/Selora-AI"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/selorahomes/Selora-AI:Q6_K

SGLang

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

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

How to use selorahomes/Selora-AI 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: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:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use selorahomes/Selora-AI with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.Selora-AI-Q6_K

List all available models

lemonade list

Hermes Agent

How to use selorahomes/Selora-AI 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: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:Q6_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use selorahomes/Selora-AI 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: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: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"

GChief117 commited on 21 days ago

Commit

c4106c2

verified ·

1 Parent(s): c26d04e

v0.4.8.1: retrain utilities LoRA for retrieval grounding

Browse files

Replaces selora-utilities.f16.gguf with a retrained utilities specialist
(same Qwen3-1.7B base, same prompt format). Trained to ground answers in
the injected RELEVANT DOCS block: cite only retrieved entries, refuse
when a device is not in the docs, and answer verdict questions directly.

Measured with the official scorers, v0.4.8 -> v0.4.8.1:
- Live integration behavioral gate (82 contracts): 79.3% -> 87.8%
- MultiHop-RAG qa_evaluate (n=60): 0.250 -> 0.650
- RGB noisy-context accuracy: 0.50 -> 0.70
- Installer pipeline end-to-end: 44/65 -> 58/65
- Honest refusal when the device is absent: 0/15 -> 15/15
- Median answer latency: 3.7s -> 0.4s

One artifact serves both runtimes: the llama-server --lora slot and the
ollama Modelfile.utilities ADAPTER. Base model and the other four
specialist LoRAs are unchanged. README gains the v0.4.8.1 benchmark
table (and corrects the RAGAS cell to the shipped model's 0.822).

Files changed (2) hide show

README.md +16 -0
selora-utilities.f16.gguf +1 -1

README.md CHANGED Viewed

@@ -209,6 +209,22 @@ Each runtime is scored two ways — the model's **Raw** envelope graded directly
 See [Evaluation](#evaluation) for what each surface measures — the LoRA adapter vs the integration vs the raw model.
 ## Quick start
 You have a choice in how you start with Selora AI:

 See [Evaluation](#evaluation) for what each surface measures — the LoRA adapter vs the integration vs the raw model.
+### v0.4.8.1 — retrieval grounding
+Updated artifacts: `selora-utilities.f16.gguf` (llama.cpp specialist) and `selora-ollama.Q6_K.gguf` (merged model). Scored with the official benchmark scorers:
+| Surface (official scorers) | Before | After | Measured on |
+|---|---|---|---|
+| Live integration behavioral gate (82 contracts, real HA) | 79.3% | **87.8%** | llama.cpp specialists |
+| MultiHop-RAG (`qa_evaluate`, n=60) | 0.250 | **0.650** | llama.cpp specialists |
+| RGB noisy-context accuracy | 0.50 | **0.70** | llama.cpp specialists |
+| RAGAS faithfulness | 0.309 | **0.822** | `selora-ollama` (merged) |
+| Installer pipeline end-to-end (65 cases) | 44 / 65 | **58 / 65** | llama.cpp specialists |
+| Honest refusal, device absent (n=15) | 0 / 15 | **15 / 15** | both runtimes |
+| Median answer latency | 3.7 s | **0.4 s** | llama.cpp specialists |
+Same base (`qwen3_17b_base.Q6_K.gguf`), same prompts, same `Modelfile.utilities` / llama-server `--lora` flow. The Allen-surface tables above reflect the prior build; re-measurement on this update is in progress.
 ## Quick start
 You have a choice in how you start with Selora AI:

selora-utilities.f16.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1e47028cbc3ad81252853bc363921764456d50a1329d41e4ded3f2b7a9b3af9
 size 19938528

 version https://git-lfs.github.com/spec/v1
+oid sha256:c28d2eb12d0f27d3d3a6b35fab7ec97972b6c945e8b702734432eed8eb6afa77
 size 19938528