Instructions to use IngeniumDL/ingenium-expert-lms-3b-instruct-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use IngeniumDL/ingenium-expert-lms-3b-instruct-gguf 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 IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf IngeniumDL/ingenium-expert-lms-3b-instruct-gguf: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 IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf IngeniumDL/ingenium-expert-lms-3b-instruct-gguf: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 IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0

Use Docker

docker model run hf.co/IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0

LM Studio
Jan
Ollama
How to use IngeniumDL/ingenium-expert-lms-3b-instruct-gguf with Ollama:
```
ollama run hf.co/IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0
```

Unsloth Studio

How to use IngeniumDL/ingenium-expert-lms-3b-instruct-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for IngeniumDL/ingenium-expert-lms-3b-instruct-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for IngeniumDL/ingenium-expert-lms-3b-instruct-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for IngeniumDL/ingenium-expert-lms-3b-instruct-gguf to start chatting

How to use IngeniumDL/ingenium-expert-lms-3b-instruct-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use IngeniumDL/ingenium-expert-lms-3b-instruct-gguf with Docker Model Runner:
```
docker model run hf.co/IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0
```

Lemonade

How to use IngeniumDL/ingenium-expert-lms-3b-instruct-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0

Run and chat with the model

lemonade run user.ingenium-expert-lms-3b-instruct-gguf-Q8_0

List all available models

lemonade list

Hermes Agent

How to use IngeniumDL/ingenium-expert-lms-3b-instruct-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0

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 IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use IngeniumDL/ingenium-expert-lms-3b-instruct-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0

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 "IngeniumDL/ingenium-expert-lms-3b-instruct-gguf:Q8_0" \
  --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"

ingenium-expert-lms-3b-instruct-gguf / docker-compose.cpu.yml

ArnaudIngenium

Paquet complet : harnais, docker-compose CPU, CLI, registres

3238f46 verified about 1 month ago

Raw

History Blame Contribute Delete

1.42 kB

	# Paquet de déploiement CPU Ingenium Expert LMS 3B Instruct — candidat Ollama.
	#
	# Variante de docker-compose.yml qui remplace vLLM/GPU par Ollama/CPU. Le
	# harnais reste l'unique point d'entrée public (127.0.0.1:8080) ; Ollama
	# reste sur le réseau interne du compose et n'est jamais joignable
	# directement.
	#
	# Usage :
	# GGUF_PATH=./ingenium-expert-lms-3b-instruct-grounded-v0.1.0-Q8_0.gguf docker compose -f docker-compose.cpu.yml up --build
	#
	# curl -X POST http://127.0.0.1:8080/ask \
	# -H "Content-Type: application/json" \
	# -d '{"question": "Comment créer un utilisateur ?", "context": {...context-v1...}}'

	services:
	ollama:
	build:
	context: .
	dockerfile: docker/ollama/Dockerfile
	environment:
	MODEL_NAME: ingenium-expert-lms-3b-instruct
	volumes:
	- ${GGUF_PATH:?GGUF_PATH requis}:/model/model.gguf:ro
	- ./deploy/ollama/Modelfile.ingenium-3b:/model/Modelfile:ro
	healthcheck:
	test: ["CMD-SHELL", "ollama list \| grep -q \"$$MODEL_NAME\""]
	interval: 10s
	timeout: 5s
	retries: 60
	start_period: 120s

	harness:
	build:
	context: .
	dockerfile: harness/Dockerfile
	environment:
	VLLM_BASE_URL: http://ollama:11434/v1
	MODEL_NAME: ingenium-expert-lms-3b-instruct
	MAX_NEW_TOKENS: "128"
	ports:
	- "127.0.0.1:8080:8080"
	depends_on:
	ollama:
	condition: service_healthy