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/cb_gate.py from RegalInvader/Marco-Nano-Instruct-GGUF: direct link, hf CLI and curl.
- Browser
- Download file 2.53 kB
-
https://huggingface.co/RegalInvader/Marco-Nano-Instruct-GGUF/resolve/main/code/scripts/cb_gate.py
- Command line
-
hf download hf://RegalInvader/Marco-Nano-Instruct-GGUF/code/scripts/cb_gate.py
-
curl -L -o cb_gate.py https://huggingface.co/RegalInvader/Marco-Nano-Instruct-GGUF/resolve/main/code/scripts/cb_gate.py
2.53 kB
| #!/usr/bin/env python3 | |
| """D-58 gate: a codebook student exactly as imported, before any training, exported packed. Its GGUF must be the | |
| llama.cpp source file's expert tensors byte for byte (`t27_gguf.py build` then `cb_gate.py compare` on gen). | |
| python scripts/cb_gate.py export --config configs/p6/CB3a.yaml --out $MT_DATA/runs/p6-gate-CB3a/packed/tok_0 | |
| python scripts/cb_gate.py compare --ours <gguf> --source <llama.cpp gguf> | |
| """ | |
| from __future__ import annotations | |
| import argparse | |
| import json | |
| import os | |
| import sys | |
| from pathlib import Path | |
| import numpy as np | |
| import torch | |
| import yaml | |
| REPO = Path(__file__).resolve().parent.parent | |
| sys.path.insert(0, str(REPO / "src")) | |
| from lowbit.model import student as st # noqa: E402 | |
| from lowbit.quant.ternary import QuantSpec # noqa: E402 | |
| def export(a) -> None: | |
| cfg = yaml.safe_load(open(a.config)) | |
| prec = st.Precision.load(REPO / cfg["model"]["precision_map"]) | |
| prec.experts = QuantSpec(method=cfg["quant"]["method"], group_size=cfg["quant"]["group_size"]) | |
| model = st.load_student(cfg["model"]["teacher"], prec, quant=True, device=a.device) | |
| print(json.dumps(st.export_packed_student(model, a.out))[:300]) | |
| def compare(a) -> None: | |
| sys.path.insert(0, os.environ.get("MT_LLAMA", "/path/to/llama.cpp") + "/gguf-py") | |
| import gguf | |
| ours = {t.name: t for t in gguf.GGUFReader(a.ours).tensors} | |
| src = {t.name: t for t in gguf.GGUFReader(a.source).tensors} | |
| diff = {"experts": [], "other": []} | |
| for name, t in src.items(): | |
| same = (name in ours and ours[name].tensor_type == t.tensor_type | |
| and np.asarray(ours[name].data).tobytes() == np.asarray(t.data).tobytes()) | |
| if not same: | |
| diff["experts" if "_exps" in name else "other"].append(name) | |
| print(json.dumps({"tensors": len(src), "missing": sorted(set(src) - set(ours)), | |
| "expert_mismatches": diff["experts"], "other_mismatches": diff["other"][:20], | |
| "n_other_mismatches": len(diff["other"])})) | |
| def main() -> None: | |
| p = argparse.ArgumentParser() | |
| sub = p.add_subparsers(dest="cmd", required=True) | |
| e = sub.add_parser("export") | |
| e.add_argument("--config", required=True) | |
| e.add_argument("--out", required=True) | |
| e.add_argument("--device", default="cuda") | |
| c = sub.add_parser("compare") | |
| c.add_argument("--ours", required=True) | |
| c.add_argument("--source", required=True) | |
| a = p.parse_args() | |
| export(a) if a.cmd == "export" else compare(a) | |
| if __name__ == "__main__": | |
| main() | |