Instructions to use RegalInvader/Marco-Nano-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 RegalInvader/Marco-Nano-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 RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0
# Run inference directly in the terminal:
llama cli -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0
# Run inference directly in the terminal:
llama cli -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Use Docker

docker model run hf.co/RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Llama new
LM Studio
Jan

vLLM

How to use RegalInvader/Marco-Nano-Instruct-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Ollama
How to use RegalInvader/Marco-Nano-Instruct-GGUF with Ollama:
```
ollama run hf.co/RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0
```
Unsloth Desktop

How to use RegalInvader/Marco-Nano-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 RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

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": "RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use RegalInvader/Marco-Nano-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0
```

Lemonade

How to use RegalInvader/Marco-Nano-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Run and chat with the model

lemonade run user.Marco-Nano-Instruct-GGUF-TQ1_0

List all available models

lemonade list

Hermes Agent

How to use RegalInvader/Marco-Nano-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 RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_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 RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RegalInvader/Marco-Nano-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 RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_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 "RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_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"

Marco-Nano-Instruct-GGUF / code /src /lowbit /eval /retention.py

RegalInvader

Release: Marco-Nano-Instruct 1-, 2- and 3-bit GGUF for phones

e5235fb verified 4 days ago

Raw History Blame Contribute Delete

1.34 kB

"""Retention (spec §7): R = s / t and chance-corrected R_c = (s - c) / (t - c), per task and as means."""
from __future__ import annotations


def chance_for(task: str, chance: dict) -> float:
    return float(chance.get(task, chance.get("default", 0.0)))


def retention(student: dict[str, float], teacher: dict[str, float], chance: dict) -> dict:
    rows = {}
    for task in student:
        if task not in teacher:
            continue
        s, t, c = student[task], teacher[task], chance_for(task, chance)
        rows[task] = {"student": s, "teacher": t, "chance": c, "R": s / t if t else float("nan"),
                      "R_c": (s - c) / (t - c) if t != c else float("nan")}
    n = len(rows)
    mean = {"R": sum(r["R"] for r in rows.values()) / n, "R_c": sum(r["R_c"] for r in rows.values()) / n} if n else {}
    return {"tasks": rows, "mean": mean}


def markdown(ret: dict, title: str) -> str:
    lines = [f"## {title}", "", "| Task | Teacher | Student | R | R_c |", "|---|---:|---:|---:|---:|"]
    for task, r in ret["tasks"].items():
        lines.append(f"| {task} | {100 * r['teacher']:.1f} | {100 * r['student']:.1f} | {r['R']:.3f} | {r['R_c']:.3f} |")
    if ret["mean"]:
        lines.append(f"| **mean** | | | **{ret['mean']['R']:.3f}** | **{ret['mean']['R_c']:.3f}** |")
    return "\n".join(lines) + "\n"

	"""Retention (spec §7): R = s / t and chance-corrected R_c = (s - c) / (t - c), per task and as means."""
	from __future__ import annotations


	def chance_for(task: str, chance: dict) -> float:
	return float(chance.get(task, chance.get("default", 0.0)))


	def retention(student: dict[str, float], teacher: dict[str, float], chance: dict) -> dict:
	rows = {}
	for task in student:
	if task not in teacher:
	continue
	s, t, c = student[task], teacher[task], chance_for(task, chance)
	rows[task] = {"student": s, "teacher": t, "chance": c, "R": s / t if t else float("nan"),
	"R_c": (s - c) / (t - c) if t != c else float("nan")}
	n = len(rows)
	mean = {"R": sum(r["R"] for r in rows.values()) / n, "R_c": sum(r["R_c"] for r in rows.values()) / n} if n else {}
	return {"tasks": rows, "mean": mean}


	def markdown(ret: dict, title: str) -> str:
	lines = [f"## {title}", "", "\| Task \| Teacher \| Student \| R \| R_c \|", "\|---\|---:\|---:\|---:\|---:\|"]
	for task, r in ret["tasks"].items():
	lines.append(f"\| {task} \| {100 * r['teacher']:.1f} \| {100 * r['student']:.1f} \| {r['R']:.3f} \| {r['R_c']:.3f} \|")
	if ret["mean"]:
	lines.append(f"\| mean \| \| \| {ret['mean']['R']:.3f} \| {ret['mean']['R_c']:.3f} \|")
	return "\n".join(lines) + "\n"