Text Generation
GGUF
llama.cpp
pocketpal
on-device
Mixture of Experts
multilingual
quantization
distillation
1-bit
2-bit
3-bit
conversational
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
- llama.cpp
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
- Pi
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"
Download code/scripts/card_tables.py from RegalInvader/Marco-Nano-Instruct-GGUF: direct link, hf CLI and curl.
- Browser
- Download file 3.6 kB
-
https://huggingface.co/RegalInvader/Marco-Nano-Instruct-GGUF/resolve/main/code/scripts/card_tables.py
- Command line
-
hf download hf://RegalInvader/Marco-Nano-Instruct-GGUF/code/scripts/card_tables.py
-
curl -L -o card_tables.py https://huggingface.co/RegalInvader/Marco-Nano-Instruct-GGUF/resolve/main/code/scripts/card_tables.py
3.6 kB
| #!/usr/bin/env python3 | |
| """Model-card tables from the measured results (D-59), so the card's numbers are copied by code, never by hand. | |
| Reads reports/compare/<name>.summary.json (fast suite), .full.summary.json (full suite), .code.summary.json | |
| (HumanEval+/MBPP+) and the lineup file (release/lineup.yaml: which result names appear, under which labels, and the | |
| phone speeds), and fills the {{TABLE_*}} markers of a card template. | |
| python scripts/card_tables.py --template release/card_gguf.md --lineup release/lineup.yaml --out README.md | |
| """ | |
| from __future__ import annotations | |
| import argparse | |
| import json | |
| import re | |
| from pathlib import Path | |
| import yaml | |
| REPO = Path(__file__).resolve().parents[1] | |
| CMP = REPO / "reports" / "compare" | |
| def load(name: str, suffix: str) -> dict | None: | |
| p = CMP / f"{name}{suffix}.summary.json" | |
| return json.loads(p.read_text()) if p.exists() else None | |
| def pct(x: float | None) -> str: | |
| return "—" if x is None else f"{100 * x:.1f}" | |
| def gb(n: int | None) -> str: | |
| return "—" if not n else f"{n / 1e9:.2f} GB" | |
| def table(rows: list[dict], cols: list[tuple[str, str, str]], suffix: str, bold: set[str]) -> str: | |
| """cols: (header, summary key, group) — key 'groups' entries as percentages.""" | |
| head = "| Model | File | " + " | ".join(c[0] for c in cols) + " |" | |
| out = [head, "|" + "---|" * (len(cols) + 2)] | |
| for r in rows: | |
| s = load(r["result"], suffix) | |
| if s is None: | |
| continue | |
| cells = [pct(s["groups"].get(c[1])) for c in cols] | |
| label = f"**{r['label']}**" if r["result"] in bold else r["label"] | |
| out.append(f"| {label} | {gb(s.get('bytes'))} | " + " | ".join(cells) + " |") | |
| return "\n".join(out) | |
| def main() -> None: | |
| ap = argparse.ArgumentParser() | |
| ap.add_argument("--template", type=Path, required=True) | |
| ap.add_argument("--lineup", type=Path, required=True) | |
| ap.add_argument("--out", type=Path, required=True) | |
| a = ap.parse_args() | |
| L = yaml.safe_load(a.lineup.read_text()) | |
| ours = {r["result"] for r in L["ours"]} | |
| rows = L["ours"] + L["reference"] + L["others"] | |
| tables = { | |
| "TABLE_FAST": table(rows, [("MMLU-Redux", "MMLU-Redux", ""), ("Global-MMLU-Lite (5)", "Global-MMLU (5 lang)", ""), | |
| ("Belebele (5)", "Belebele (5 lang)", ""), ("GSM8K-250", "GSM8K-250", "")], "", ours), | |
| "TABLE_FULL": table(rows, [("MMLU-Pro", "MMLU-Pro (direct)", ""), ("Global-MMLU (5 more)", "Global-MMLU (de es fr ja ru)", ""), | |
| ("MATH-500", "MATH-500", ""), ("IFEval (prompt)", "IFEval (prompt strict)", ""), | |
| ("IFEval (instr.)", "IFEval (instruction strict)", "")], ".full", ours), | |
| "TABLE_CODE": table(rows, [("HumanEval+", "HumanEval+", ""), ("MBPP+", "MBPP+", "")], ".code", ours), | |
| } | |
| sp = ["| File | Size | Prompt (tok/s) | Generation (tok/s) |", "|---|---|---|---|"] | |
| for r in rows: | |
| if r.get("pixel"): | |
| s = load(r["result"], "") or load(r["result"], ".full") or {} | |
| sp.append(f"| {('**' + r['label'] + '**') if r['result'] in ours else r['label']} | {gb(s.get('bytes'))} | " | |
| f"{r['pixel'][0]} | {r['pixel'][1]} |") | |
| tables["TABLE_PIXEL"] = "\n".join(sp) | |
| text = a.template.read_text() | |
| for k, v in tables.items(): | |
| text = text.replace("{{" + k + "}}", v) | |
| left = re.findall(r"\{\{[A-Z_]+\}\}", text) | |
| if left: | |
| raise SystemExit(f"unfilled markers: {left}") | |
| a.out.write_text(text) | |
| print(f"wrote {a.out}") | |
| if __name__ == "__main__": | |
| main() | |