Instructions to use QuantFactory/magnum-v2-12b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/magnum-v2-12b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/magnum-v2-12b-GGUF",
	filename="magnum-12b-v2.Q2_K.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 QuantFactory/magnum-v2-12b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/magnum-v2-12b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/magnum-v2-12b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/magnum-v2-12b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/magnum-v2-12b-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 QuantFactory/magnum-v2-12b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/magnum-v2-12b-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 QuantFactory/magnum-v2-12b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/magnum-v2-12b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/magnum-v2-12b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/magnum-v2-12b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/magnum-v2-12b-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": "QuantFactory/magnum-v2-12b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/magnum-v2-12b-GGUF:Q4_K_M

Ollama
How to use QuantFactory/magnum-v2-12b-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/magnum-v2-12b-GGUF:Q4_K_M
```

Unsloth Studio

How to use QuantFactory/magnum-v2-12b-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 QuantFactory/magnum-v2-12b-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 QuantFactory/magnum-v2-12b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/magnum-v2-12b-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use QuantFactory/magnum-v2-12b-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/magnum-v2-12b-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/magnum-v2-12b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/magnum-v2-12b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.magnum-v2-12b-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/magnum-12b-v2-GGUF

This is quantized version of anthracite-org/magnum-12b-v2 created using llama.cpp

Original Model Card

This is the fourth in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of Mistral-Nemo-Base-2407.

Prompting

Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:

"""<|im_start|>system
system prompt<|im_end|>
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""

Credits

Stheno dataset (filtered)
NobodyExistsOnTheInternet/claude_3.5s_single_turn_unslop_filtered
NobodyExistsOnTheInternet/PhiloGlanSharegpt
NobodyExistsOnTheInternet/Magpie-Reasoning-Medium-Subset
kalomaze/Opus_Instruct_25k
Nopm/Opus_WritingStruct
Gryphe/Sonnet3.5-SlimOrcaDedupCleaned (A ~16k rows subset)

This model has been a team effort, and the credits goes to all members of Anthracite.

Training

The training was done for 2 epochs. We used 8x NVIDIA H100 Tensor Core GPUs for the full-parameter fine-tuning of the model.

Safety

...

Downloads last month: 123

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit