Instructions to use eadx/gemma-4-E4B-it-OBLITERATED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eadx/gemma-4-E4B-it-OBLITERATED with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="eadx/gemma-4-E4B-it-OBLITERATED",
	filename="gemma-4-E4B-it-OBLITERATED-Q4_K_M.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 eadx/gemma-4-E4B-it-OBLITERATED 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 eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf eadx/gemma-4-E4B-it-OBLITERATED: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 eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf eadx/gemma-4-E4B-it-OBLITERATED: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 eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Use Docker

docker model run hf.co/eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M

LM Studio
Jan

vLLM

How to use eadx/gemma-4-E4B-it-OBLITERATED with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eadx/gemma-4-E4B-it-OBLITERATED"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eadx/gemma-4-E4B-it-OBLITERATED",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Ollama
How to use eadx/gemma-4-E4B-it-OBLITERATED with Ollama:
```
ollama run hf.co/eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M
```

Unsloth Studio

How to use eadx/gemma-4-E4B-it-OBLITERATED 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 eadx/gemma-4-E4B-it-OBLITERATED 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 eadx/gemma-4-E4B-it-OBLITERATED to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for eadx/gemma-4-E4B-it-OBLITERATED to start chatting

How to use eadx/gemma-4-E4B-it-OBLITERATED with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use eadx/gemma-4-E4B-it-OBLITERATED with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use eadx/gemma-4-E4B-it-OBLITERATED with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use eadx/gemma-4-E4B-it-OBLITERATED with Docker Model Runner:
```
docker model run hf.co/eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M
```

Lemonade

How to use eadx/gemma-4-E4B-it-OBLITERATED with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull eadx/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E4B-it-OBLITERATED-Q4_K_M

List all available models

lemonade list

gemma-4-E4B-it-OBLITERATED / abliteration_metadata.json

eadx

Duplicate from OBLITERATUS/gemma-4-E4B-it-OBLITERATED

28d54c7 3 months ago

Raw

History Blame Contribute Delete

1.81 kB

	{
	"source_model": "google/gemma-4-E4B-it",
	"technique": "refusal_direction_ablation",
	"method": "aggressive",
	"method_config": {
	"n_directions": 2,
	"direction_method": "svd",
	"norm_preserve": true,
	"regularization": 0.0,
	"refinement_passes": 3,
	"project_biases": true,
	"use_chat_template": true,
	"use_whitened_svd": true,
	"true_iterative_refinement": true,
	"winsorize_activations": true,
	"float_layer_interpolation": false,
	"cot_aware": false,
	"use_kl_optimization": false,
	"use_lora_ablation": false,
	"spectral_cascade": false,
	"spectral_bands": 3,
	"spectral_threshold": 0.05
	},
	"references": [
	"Arditi et al., Refusal in Language Models Is Mediated by a Single Direction (NeurIPS 2024)",
	"Gabliteration: SVD-based multi-direction extraction (arXiv:2512.18901)",
	"Norm-Preserving Biprojected Abliteration (grimjim, 2025)",
	"Young, Comparative Analysis of LLM Abliteration Methods (arXiv:2512.13655)",
	"Joad et al., More to Refusal than a Single Direction (2026)",
	"Heretic (p-e-w, 2025): Bayesian optimization, LoRA-mediated ablation, winsorization",
	"OBLITERATUS: Whitened SVD, EGA, CoT-aware, KL co-optimization, float interpolation (novel)"
	],
	"strong_layers": [
	39,
	37,
	38,
	36,
	31,
	24,
	35,
	40,
	34,
	26,
	29,
	33,
	28,
	30,
	32,
	27,
	25,
	19,
	20,
	18,
	17
	],
	"n_harmful_prompts": 842,
	"n_harmless_prompts": 842,
	"quality_metrics": {
	"perplexity": 29788.48721315417,
	"coherence": 0.1,
	"refusal_rate": 0.0,
	"kl_divergence": 12.563175201416016,
	"spectral_certification": "RED"
	},
	"kl_contributions": {},
	"cot_preserved_layers": [],
	"float_layer_weights": {},
	"lora_adapters_saved": false
	}