Instructions to use spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-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 spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-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 spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-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 spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-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 spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-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 spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF:Q4_K_M

Use Docker

docker model run hf.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-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": "spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF:Q4_K_M

Ollama
How to use spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF with Ollama:
```
ollama run hf.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF:Q4_K_M
```

Unsloth Studio

How to use spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-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 spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-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 spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF with Docker Model Runner:
```
docker model run hf.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF:Q4_K_M
```

Lemonade

How to use spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF-Q4_K_M

List all available models

lemonade list

An experimental ablation of Gemma-3-27B-it, using the Heretic tool.

Compared to the standard configuration of Heretic, there are a few changes:

The training and test datasets used were extended compared to the default subset used by Heretic
A version of Magnitude-Preserving Orthogonal Ablation (MPOA) is used
To stay faithful to MPOA, the harmful direction to ablate is chosen from between 2 layers (Heretic's "global" direction scope)
To stay faithful to MPOA, a 99% winsorization is applied to the residuals
Some additional refusal markers were added to avoid bypassing the refusal detection with bad punctuation

To achieve strong results:

Parameter ranges were iteratively refined by looking at resulting refusal and divergence scores
The scoring function was adjusted to prioritize low-refusal results

The model name contains the properties of the ablation:

MPOA for the usage of Magnitude-Preserving Orthogonal Ablation
G for the usage of global direction scope
W for the usage of winsorization
D for the measured KL divergence
R for the number of refusals

Original: https://huggingface.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02
GGUF (standard): https://huggingface.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-GGUF
GGUF (imatrix): https://huggingface.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-i1-GGUF
MLX: https://huggingface.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.0690-R02-MLX

Downloads last month: 302

GGUF

Model size

27B params

Architecture

gemma3

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit