Instructions to use forlop/microdata-copilot-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use forlop/microdata-copilot-v3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="forlop/microdata-copilot-v3",
	filename="microdata-copilot-v3-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use forlop/microdata-copilot-v3 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 forlop/microdata-copilot-v3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf forlop/microdata-copilot-v3:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf forlop/microdata-copilot-v3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf forlop/microdata-copilot-v3:Q4_K_M

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 forlop/microdata-copilot-v3:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf forlop/microdata-copilot-v3:Q4_K_M

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 forlop/microdata-copilot-v3:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf forlop/microdata-copilot-v3:Q4_K_M

Use Docker

docker model run hf.co/forlop/microdata-copilot-v3:Q4_K_M

LM Studio
Jan
Ollama
How to use forlop/microdata-copilot-v3 with Ollama:
```
ollama run hf.co/forlop/microdata-copilot-v3:Q4_K_M
```

Unsloth Studio

How to use forlop/microdata-copilot-v3 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 forlop/microdata-copilot-v3 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 forlop/microdata-copilot-v3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for forlop/microdata-copilot-v3 to start chatting

How to use forlop/microdata-copilot-v3 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf forlop/microdata-copilot-v3:Q4_K_M

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": "forlop/microdata-copilot-v3:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use forlop/microdata-copilot-v3 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf forlop/microdata-copilot-v3:Q4_K_M

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 forlop/microdata-copilot-v3:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use forlop/microdata-copilot-v3 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf forlop/microdata-copilot-v3:Q4_K_M

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 "forlop/microdata-copilot-v3:Q4_K_M" \
  --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"

Docker Model Runner
How to use forlop/microdata-copilot-v3 with Docker Model Runner:
```
docker model run hf.co/forlop/microdata-copilot-v3:Q4_K_M
```

Lemonade

How to use forlop/microdata-copilot-v3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull forlop/microdata-copilot-v3:Q4_K_M

Run and chat with the model

lemonade run user.microdata-copilot-v3-Q4_K_M

List all available models

lemonade list

microdata.no copilot — v3.0 (q4_k_m GGUF)

A small, locally-deployable AI assistant fine-tuned to help users write microdata.no scripts and answer questions about Norwegian register-data variables published by SSB (Statistics Norway).

This repo hosts the deployed q4_k_m quantised GGUF (2.7 GB) and the companion Ollama Modelfile. Full source (training, RAG, eval, deploy) and the technical note: https://github.com/forlop/microdata-no-copilot (branch v3).

What's new in v3

Response-masking SFT — trains on the assistant completion only.
Variable/command hallucination eliminated — a retrieval-backed guardrail plus cleaner training data; 0 fictional commands across the 126-prompt eval (this was v2's dominant failure mode).
Deduplicated training set (1,667 cards) and small LoRA dropout.
Deployment fixes — GGUF metadata corrected for Qwen3.5's hybrid SSM+attention architecture (NextN/MTP layer) so Ollama loads it; the RAG layer recovers answers Ollama routes into its thinking field.

Evaluation (v3)

Metric	Value
Training eval_loss	0.274
Deterministic eval (46-prompt)	78.3%
LLM-judge, deployed q4 + RAG (80-prompt)	56.2% (95% CI 45–67%)
Fictional commands	0 / 126

On the LLM-judge metric v3 is on par with v2 (53.8%) within confidence intervals; the decisive, measurable gain is the elimination of hallucinated variables/commands. The judge rubric is claude-haiku-graded (unvalidated against human labels — see the repo's TECHNICAL_NOTE).

Quick start

# 1. Pull the GGUF from this repo (~2.7 GB, one-time)
ollama pull hf.co/forlop/microdata-copilot-v3:Q4_K_M

# 2. Clone the GitHub repo (Modelfile + RAG layer) and apply the SYSTEM prompt
git clone -b v3 https://github.com/forlop/microdata-no-copilot
cd microdata-no-copilot
ollama create microdata-copilot -f deploy/Modelfile

# 3. Try it
ollama run microdata-copilot "What is INNTEKT_LONN?"

License & data note

Model weights released under MIT. The assistant was trained with material derived from SSB's microdata.no documentation; users are responsible for complying with SSB's terms when using outputs. The RAG index (containing manual text) is not distributed here.