Instructions to use Kasper-Bankler/gemma-4-E2B-Alignment-Study with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Kasper-Bankler/gemma-4-E2B-Alignment-Study 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 Kasper-Bankler/gemma-4-E2B-Alignment-Study
# Run inference directly in the terminal:
llama cli -hf Kasper-Bankler/gemma-4-E2B-Alignment-Study

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Kasper-Bankler/gemma-4-E2B-Alignment-Study
# Run inference directly in the terminal:
llama cli -hf Kasper-Bankler/gemma-4-E2B-Alignment-Study

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 Kasper-Bankler/gemma-4-E2B-Alignment-Study
# Run inference directly in the terminal:
./llama-cli -hf Kasper-Bankler/gemma-4-E2B-Alignment-Study

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 Kasper-Bankler/gemma-4-E2B-Alignment-Study
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kasper-Bankler/gemma-4-E2B-Alignment-Study

Use Docker

docker model run hf.co/Kasper-Bankler/gemma-4-E2B-Alignment-Study

LM Studio
Jan

vLLM

How to use Kasper-Bankler/gemma-4-E2B-Alignment-Study with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kasper-Bankler/gemma-4-E2B-Alignment-Study"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kasper-Bankler/gemma-4-E2B-Alignment-Study",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kasper-Bankler/gemma-4-E2B-Alignment-Study

Ollama
How to use Kasper-Bankler/gemma-4-E2B-Alignment-Study with Ollama:
```
ollama run hf.co/Kasper-Bankler/gemma-4-E2B-Alignment-Study
```

Unsloth Studio

How to use Kasper-Bankler/gemma-4-E2B-Alignment-Study 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 Kasper-Bankler/gemma-4-E2B-Alignment-Study 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 Kasper-Bankler/gemma-4-E2B-Alignment-Study to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Kasper-Bankler/gemma-4-E2B-Alignment-Study to start chatting

How to use Kasper-Bankler/gemma-4-E2B-Alignment-Study with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kasper-Bankler/gemma-4-E2B-Alignment-Study

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Kasper-Bankler/gemma-4-E2B-Alignment-Study"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Kasper-Bankler/gemma-4-E2B-Alignment-Study with Docker Model Runner:
```
docker model run hf.co/Kasper-Bankler/gemma-4-E2B-Alignment-Study
```

Lemonade

How to use Kasper-Bankler/gemma-4-E2B-Alignment-Study with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kasper-Bankler/gemma-4-E2B-Alignment-Study

Run and chat with the model

lemonade run user.gemma-4-E2B-Alignment-Study-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Kasper-Bankler/gemma-4-E2B-Alignment-Study with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kasper-Bankler/gemma-4-E2B-Alignment-Study

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 Kasper-Bankler/gemma-4-E2B-Alignment-Study

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Kasper-Bankler/gemma-4-E2B-Alignment-Study with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kasper-Bankler/gemma-4-E2B-Alignment-Study

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 "Kasper-Bankler/gemma-4-E2B-Alignment-Study" \
  --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"

Kasper-Bankler commited on 19 days ago

Commit

cd338ca

verified ·

1 Parent(s): 7002fc0

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -15,19 +15,19 @@ tags:
 - AI-safety
 ---
-# Gemma 4 E2B - Uncensored
-This is a surgically uncensored version of `google/gemma-4-E2B-it`, achieved through **Arbitrary-Rank Ablation (ARA)**.
 ## 🔬 Ablation Methodology
-This model was uncensored using the [Heretic](https://github.com/p-e-w/heretic) framework. Instead of fine-tuning the model on unsafe data, the model's internal "refusal vector" was mathematically located and ablated at the matrix level.
 * **Technique:** Arbitrary-Rank Ablation (ARA)
 * **Trial Selected:** Trial 71
 * **KL Divergence:** `0.1650`
-**Why Trial 71?** During comparative analysis, higher ablation (e.g., Trial 129 / KL: 0.3542) successfully destroyed all censorship but resulted in severe semantic drift and "brain damage" (e.g., hallucinating when asked technical questions). Trial 71 was selected because a KL divergence of `0.1650` represents the perfect "Goldilocks" zone. It successfully bypasses the safety guardrails while preserving the model's core logic, spatial reasoning, and technical vocabulary.
 ## 💻 Hardware & Build Details

 - AI-safety
 ---
+# Gemma 4 E2B - Alignment Study
+This model is a Representation Engineering study on `google/gemma-4-E2B-it`, achieved through **Arbitrary-Rank Ablation (ARA)** to mathematically isolate and remove the model's refusal direction.
 ## 🔬 Ablation Methodology
+The model's alignment vectors were modified using the [Heretic](https://github.com/p-e-w/heretic) framework. Instead of fine-tuning the model on alternative data, the internal "refusal vector" was mathematically located and ablated at the matrix level.
 * **Technique:** Arbitrary-Rank Ablation (ARA)
 * **Trial Selected:** Trial 71
 * **KL Divergence:** `0.1650`
+*
+**Why Trial 71?** During comparative analysis, higher ablation (e.g., Trial 129 / KL: 0.3542) successfully removed all refusal behaviors but resulted in severe semantic drift and performance degradation (e.g., hallucinating when asked technical questions). Trial 71 was selected because a KL divergence of `0.1650` represents an optimal threshold. It successfully alters the safety alignment while preserving the model's core logic, spatial reasoning, and technical vocabulary.
 ## 💻 Hardware & Build Details