Instructions to use anthracite-org/magnum-v2-123b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anthracite-org/magnum-v2-123b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="anthracite-org/magnum-v2-123b-gguf",
	filename="magnum-v2-123b-iq1_s.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 anthracite-org/magnum-v2-123b-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 anthracite-org/magnum-v2-123b-gguf:IQ1_S
# Run inference directly in the terminal:
llama cli -hf anthracite-org/magnum-v2-123b-gguf:IQ1_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf anthracite-org/magnum-v2-123b-gguf:IQ1_S
# Run inference directly in the terminal:
llama cli -hf anthracite-org/magnum-v2-123b-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 anthracite-org/magnum-v2-123b-gguf:IQ1_S
# Run inference directly in the terminal:
./llama-cli -hf anthracite-org/magnum-v2-123b-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 anthracite-org/magnum-v2-123b-gguf:IQ1_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf anthracite-org/magnum-v2-123b-gguf:IQ1_S

Use Docker

docker model run hf.co/anthracite-org/magnum-v2-123b-gguf:IQ1_S

LM Studio
Jan

vLLM

How to use anthracite-org/magnum-v2-123b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anthracite-org/magnum-v2-123b-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": "anthracite-org/magnum-v2-123b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anthracite-org/magnum-v2-123b-gguf:IQ1_S

Ollama
How to use anthracite-org/magnum-v2-123b-gguf with Ollama:
```
ollama run hf.co/anthracite-org/magnum-v2-123b-gguf:IQ1_S
```

Unsloth Studio

How to use anthracite-org/magnum-v2-123b-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 anthracite-org/magnum-v2-123b-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 anthracite-org/magnum-v2-123b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for anthracite-org/magnum-v2-123b-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use anthracite-org/magnum-v2-123b-gguf with Docker Model Runner:
```
docker model run hf.co/anthracite-org/magnum-v2-123b-gguf:IQ1_S
```

Lemonade

How to use anthracite-org/magnum-v2-123b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull anthracite-org/magnum-v2-123b-gguf:IQ1_S

Run and chat with the model

lemonade run user.magnum-v2-123b-gguf-IQ1_S

List all available models

lemonade list

How much VRAM do you need (you = Anthracite)

by AIGUYCONTENT - opened Aug 27, 2024

Discussion

AIGUYCONTENT

Aug 27, 2024

I noticed in your description that it said you did not continue training for an additional epoch due to the cost.

Out of sheer curiosity and nothing else--what if you only had 168GB of VRAM at your disposal (All 3090s and different mfg)? Would training a model like Magnum 123b be impractical due to the length of time it would take? Would that be enough for you to train a 70B model? And if so--do you guys take requests?

lucyknada

Anthracite org Aug 27, 2024

Hi there, thanks for voicing your interest in providing compute! however it didn't properly fit even with liger kernels into 8xh100 (640GB of vram), we had to use mi300x (1.5TB of vram) the last few times for anything 70b/123b, so it's not even the time that would prevent us from using this offer for these models but the OOM.

lucyknada changed discussion status to closed Aug 27, 2024

AIGUYCONTENT

Aug 29, 2024

Well thanks and keep up the good work! Magnum 123B is my new favorite model. In fact, it caused me to cancel my Claude3 subscription. Really appreciate you guys giving these great models away to the community. Thank you!!!

lucyknada

Anthracite org Aug 29, 2024

Thanks for such positive feedback! I'm glad we were able to give you claude at home!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment