Instructions to use kabachuha/gemma3-4b-it-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kabachuha/gemma3-4b-it-abliterated with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="kabachuha/gemma3-4b-it-abliterated")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kabachuha/gemma3-4b-it-abliterated", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kabachuha/gemma3-4b-it-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kabachuha/gemma3-4b-it-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kabachuha/gemma3-4b-it-abliterated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kabachuha/gemma3-4b-it-abliterated

SGLang

How to use kabachuha/gemma3-4b-it-abliterated with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "kabachuha/gemma3-4b-it-abliterated" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kabachuha/gemma3-4b-it-abliterated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "kabachuha/gemma3-4b-it-abliterated" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kabachuha/gemma3-4b-it-abliterated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kabachuha/gemma3-4b-it-abliterated with Docker Model Runner:
```
docker model run hf.co/kabachuha/gemma3-4b-it-abliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Gemma 3 abliterated

This is Gemma 3 4b with [abliteration technique] (https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction) applied to reduce refusals. (with high scale_factor=2.0 as it was very stubborn originally)

Tested its work in VLLM. It does give the disclaimers sometimes, but more or less often executes the instructions as needed, and the disclaimers are less aggressive.