Instructions to use Naphula/Magistaroth-24B-v1.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula/Magistaroth-24B-v1.1-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Naphula/Magistaroth-24B-v1.1-GGUF", dtype="auto")

llama-cpp-python

How to use Naphula/Magistaroth-24B-v1.1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Naphula/Magistaroth-24B-v1.1-GGUF",
	filename="Magistaroth-24B-v1.1-Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Naphula/Magistaroth-24B-v1.1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Naphula/Magistaroth-24B-v1.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Naphula/Magistaroth-24B-v1.1-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 Naphula/Magistaroth-24B-v1.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Naphula/Magistaroth-24B-v1.1-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 Naphula/Magistaroth-24B-v1.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Naphula/Magistaroth-24B-v1.1-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 Naphula/Magistaroth-24B-v1.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Naphula/Magistaroth-24B-v1.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Naphula/Magistaroth-24B-v1.1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Naphula/Magistaroth-24B-v1.1-GGUF with Ollama:
```
ollama run hf.co/Naphula/Magistaroth-24B-v1.1-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Naphula/Magistaroth-24B-v1.1-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 Naphula/Magistaroth-24B-v1.1-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 Naphula/Magistaroth-24B-v1.1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Naphula/Magistaroth-24B-v1.1-GGUF to start chatting

Docker Model Runner
How to use Naphula/Magistaroth-24B-v1.1-GGUF with Docker Model Runner:
```
docker model run hf.co/Naphula/Magistaroth-24B-v1.1-GGUF:Q4_K_M
```

Lemonade

How to use Naphula/Magistaroth-24B-v1.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Naphula/Magistaroth-24B-v1.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Magistaroth-24B-v1.1-GGUF-Q4_K_M

List all available models

lemonade list

⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use Mistral Tekken chat template.

🌌 Magistaroth 24B v1.1 GGUF

Merge Method

A custom merge method known as pdq has been invented. Instead of using its own yaml, it acts as a post-merge processor which applies directly to the merged model using the original yaml. pdq aims to enhance creativity by re-scanning the original donor models, encouraging them to explore the 'dark matter' regions of the vectors to synergistically augment the merged base with more unique novelty. For Magistaroth v1.1, I tested both the v1 Della → PDQ → MPOA and Della → MPOA → PDQ.

It turns out that both are very creative, and the MPOA → PDQ is interesting because it doesn't re-introduce any refusals, however, PDQ → MPOA is much smarter. The difference in Q0 bench reflects this (9451 vs 12648). Scale 1.2 was the ablation threshold required to disable refusals. This has resulted in the most creative, detailed, and uncensored variant of the configurations tested.

Bugs

A small risk of increased artifacts (missing spaces, word misspelled or repeated) might be noticed due to pdq pushing the limits of what's possible with transformers. These are rare and can be edited out if needed.

Fully Uncensored

An unablated PDQ version was also tested (it has refusals) but it seems the ablated versions are more popular so I'm just releasing this one for now.

Settings

Recommended temp 1.0 and topnsigma 1.25
Mistral Tekken chat template

Downloads last month: 22

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

4-bit

6-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Naphula/Magistaroth-24B-v1.1-GGUF

Base model

DarkArtsForge/Magistaroth-24B-v1.1

Quantized

(9)

this model