Instructions to use Disya/Marco-Nano-Instruct-Q6_K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Disya/Marco-Nano-Instruct-Q6_K-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Disya/Marco-Nano-Instruct-Q6_K-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Disya/Marco-Nano-Instruct-Q6_K-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 Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K

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 Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K

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 Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K

Use Docker

docker model run hf.co/Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K

LM Studio
Jan
Ollama
How to use Disya/Marco-Nano-Instruct-Q6_K-GGUF with Ollama:
```
ollama run hf.co/Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K
```
Unsloth Desktop

How to use Disya/Marco-Nano-Instruct-Q6_K-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K

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": "Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Disya/Marco-Nano-Instruct-Q6_K-GGUF with Docker Model Runner:
```
docker model run hf.co/Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K
```

Lemonade

How to use Disya/Marco-Nano-Instruct-Q6_K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K

Run and chat with the model

lemonade run user.Marco-Nano-Instruct-Q6_K-GGUF-Q6_K

List all available models

lemonade list

Hermes Agent

How to use Disya/Marco-Nano-Instruct-Q6_K-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 Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K

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 Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Disya/Marco-Nano-Instruct-Q6_K-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K

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 "Disya/Marco-Nano-Instruct-Q6_K-GGUF:Q6_K" \
  --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-Q6_K-GGUF / README.md

Disya

Upload README.md with huggingface_hub

2f2a5d5 verified 5 months ago

preview code

Raw

History Blame Contribute Delete

2.38 kB

	---
	license: apache-2.0
	language:
	- en
	- zh
	- ar
	- de
	- es
	- fr
	- ko
	- ja
	- pt
	- tr
	- id
	- it
	- nl
	- pl
	- ru
	- vi
	- th
	- he
	- uk
	- ms
	- bn
	- cs
	- ur
	- kk
	- el
	- ro
	- hu
	- ne
	- az
	library_name: transformers
	tags:
	- moe
	- mixture-of-experts
	- multilingual
	- upcycling
	- llama-cpp
	- gguf-my-repo
	datasets:
	- allenai/Dolci-Instruct-SFT
	- nvidia/Nemotron-Cascade-2-SFT-Data
	- nvidia/Nemotron-RL-instruction_following
	- nvidia/Nemotron-RL-instruction_following-structured_outputs
	- nvidia/Nemotron-RL-ReasoningGym-v1
	- nvidia/Nemotron-RL-knowledge-mcqa
	- nvidia/Nemotron-Cascade-RL-RLHF
	- BytedTsinghua-SIA/DAPO-Math-17k
	- Skywork/Skywork-OR1-RL-Data
	- nvidia/Nemotron-SFT-Multilingual-v1
	base_model: AIDC-AI/Marco-Nano-Instruct
	---

	# Disya/Marco-Nano-Instruct-Q6_K-GGUF
	This model was converted to GGUF format from [`AIDC-AI/Marco-Nano-Instruct`](https://huggingface.co/AIDC-AI/Marco-Nano-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
	Refer to the [original model card](https://huggingface.co/AIDC-AI/Marco-Nano-Instruct) for more details on the model.

	## Use with llama.cpp
	Install llama.cpp through brew (works on Mac and Linux)

	```bash
	brew install llama.cpp

	```
	Invoke the llama.cpp server or the CLI.

	### CLI:
	```bash
	llama-cli --hf-repo Disya/Marco-Nano-Instruct-Q6_K-GGUF --hf-file marco-nano-instruct-q6_k.gguf -p "The meaning to life and the universe is"
	```

	### Server:
	```bash
	llama-server --hf-repo Disya/Marco-Nano-Instruct-Q6_K-GGUF --hf-file marco-nano-instruct-q6_k.gguf -c 2048
	```

	Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

	Step 1: Clone llama.cpp from GitHub.
	```
	git clone https://github.com/ggerganov/llama.cpp
	```

	Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
	```
	cd llama.cpp && LLAMA_CURL=1 make
	```

	Step 3: Run inference through the main binary.
	```
	./llama-cli --hf-repo Disya/Marco-Nano-Instruct-Q6_K-GGUF --hf-file marco-nano-instruct-q6_k.gguf -p "The meaning to life and the universe is"
	```
	or
	```
	./llama-server --hf-repo Disya/Marco-Nano-Instruct-Q6_K-GGUF --hf-file marco-nano-instruct-q6_k.gguf -c 2048
	```