Instructions to use dranger003/Smaug-72B-v0.1-iMat.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 dranger003/Smaug-72B-v0.1-iMat.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 dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S
# Run inference directly in the terminal:
llama cli -hf dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S
# Run inference directly in the terminal:
llama cli -hf dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S

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 dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S
# Run inference directly in the terminal:
./llama-cli -hf dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S

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 dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S

Use Docker

docker model run hf.co/dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S

LM Studio
Jan

vLLM

How to use dranger003/Smaug-72B-v0.1-iMat.GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dranger003/Smaug-72B-v0.1-iMat.GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dranger003/Smaug-72B-v0.1-iMat.GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S

Ollama
How to use dranger003/Smaug-72B-v0.1-iMat.GGUF with Ollama:
```
ollama run hf.co/dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S
```
Unsloth Desktop
Docker Model Runner
How to use dranger003/Smaug-72B-v0.1-iMat.GGUF with Docker Model Runner:
```
docker model run hf.co/dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S
```

Lemonade

How to use dranger003/Smaug-72B-v0.1-iMat.GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dranger003/Smaug-72B-v0.1-iMat.GGUF:IQ1_S

Run and chat with the model

lemonade run user.Smaug-72B-v0.1-iMat.GGUF-IQ1_S

List all available models

lemonade list

Atomic Chat

GGUF importance matrix (imatrix) quants for https://huggingface.co/abacusai/Smaug-72B-v0.1
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.

Update 2024-03-14:

New quant IQ1_S using latest commit 4755afd1.

Update 2024-03-02:

New quants IQ2_S/IQ2_M, requires commit a33e6a0d or later.
The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a general purpose imatrix calibration dataset.
This is a different calibration dataset than the previous quants I posted so we can compare the quality

Llama-2 conversation template and system prompt set to the Qwen system prompt.

Layers	Context	Template
80	32768	[INST] <<SYS>> {instructions} <</SYS>> {prompt} [/INST] {response}

Downloads last month: 139

GGUF

Model size

72B params

Architecture

llama

Hardware compatibility

1-bit

2-bit

3-bit