Instructions to use NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF",
	filename="nb-llama-3.1-8b-instruct-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-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 NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF: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 NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF: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 NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-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": "NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M

Ollama
How to use NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF 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 NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF 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 NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF to start chatting

How to use NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF: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": "NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-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 NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF: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 NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF: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 "NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF: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 NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

NB-Llama-3.1-8B-Instruct-Q4_K_M-GGUF

This model is a quantized version of the original NB-Llama-3.1-8B-Instruct, converted into the GGUF format using llama.cpp. Quantization significantly reduces the model's memory footprint, enabling efficient inference on a wide range of hardware, including personal devices, without compromising too much quality. These quantized models are mainly provided so that people can test out the models with moderate hardware. If you want to benchmark the models or further finetune the models, we strongly recommend the non-quantized versions.

What is `llama.cpp`?

llama.cpp is a versatile tool for running large language models optimized for efficiency. It supports multiple quantization formats (e.g., GGML and GGUF) and provides inference capabilities on diverse hardware, including CPUs, GPUs, and mobile devices. The GGUF format is the latest evolution, designed to enhance compatibility and performance.

Benefits of This Model

High Performance: Achieves similar quality to the original model while using significantly less memory.
Hardware Compatibility: Optimized for running on a variety of hardware, including low-resource systems.
Ease of Use: Seamlessly integrates with llama.cpp for fast and efficient inference.

Installation

Install llama.cpp using Homebrew (works on Mac and Linux):

brew install llama.cpp

Usage Instructions

Using with `llama.cpp`

To use this quantized model with llama.cpp, follow the steps below:

CLI:

llama-cli --hf-repo NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF --hf-file nb-llama-3.1-8b-instruct-q4_k_m.gguf -p "Your prompt here"

Server:

llama-server --hf-repo NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF --hf-file nb-llama-3.1-8b-instruct-q4_k_m.gguf -c 2048

For more information, refer to the llama.cpp repository.

Additional Resources

Citing & Authors

The model was trained and documentation written by Per Egil Kummervold

Funding and Acknowledgement

Training this model was supported by Google’s TPU Research Cloud (TRC), which generously supplied us with Cloud TPUs essential for our computational needs..

Downloads last month: 19

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

Collection including NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF

NB-Llama 3.x Quant

Collection

Quantized version of the NB-Llama 3.x models. Due to hardware issues, we have still not been able to make quantized version of the 70B models. • 6 items • Updated 22 days ago

NB-Llama-3.1-8B-Instruct-Q4_K_M-GGUF

What is llama.cpp?

Benefits of This Model

Installation

Usage Instructions

Using with llama.cpp

CLI:

Server:

Additional Resources

Citing & Authors

Funding and Acknowledgement

Collection including NbAiLab/nb-llama-3.1-8B-Instruct-Q4_K_M-GGUF

What is `llama.cpp`?

Using with `llama.cpp`