Instructions to use Testament200156/old-MakeGemma3-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Testament200156/old-MakeGemma3-abliterated with Transformers:

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

pipe = pipeline("image-text-to-text", model="Testament200156/old-MakeGemma3-abliterated")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Testament200156/old-MakeGemma3-abliterated")
model = AutoModelForMultimodalLM.from_pretrained("Testament200156/old-MakeGemma3-abliterated", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Testament200156/old-MakeGemma3-abliterated 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 Testament200156/old-MakeGemma3-abliterated:F16
# Run inference directly in the terminal:
llama cli -hf Testament200156/old-MakeGemma3-abliterated:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Testament200156/old-MakeGemma3-abliterated:F16
# Run inference directly in the terminal:
llama cli -hf Testament200156/old-MakeGemma3-abliterated:F16

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 Testament200156/old-MakeGemma3-abliterated:F16
# Run inference directly in the terminal:
./llama-cli -hf Testament200156/old-MakeGemma3-abliterated:F16

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 Testament200156/old-MakeGemma3-abliterated:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Testament200156/old-MakeGemma3-abliterated:F16

Use Docker

docker model run hf.co/Testament200156/old-MakeGemma3-abliterated:F16

LM Studio
Jan

vLLM

How to use Testament200156/old-MakeGemma3-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Testament200156/old-MakeGemma3-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Testament200156/old-MakeGemma3-abliterated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Testament200156/old-MakeGemma3-abliterated:F16

SGLang

How to use Testament200156/old-MakeGemma3-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 "Testament200156/old-MakeGemma3-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": "Testament200156/old-MakeGemma3-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 "Testament200156/old-MakeGemma3-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": "Testament200156/old-MakeGemma3-abliterated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Testament200156/old-MakeGemma3-abliterated with Ollama:
```
ollama run hf.co/Testament200156/old-MakeGemma3-abliterated:F16
```
Unsloth Desktop
Docker Model Runner
How to use Testament200156/old-MakeGemma3-abliterated with Docker Model Runner:
```
docker model run hf.co/Testament200156/old-MakeGemma3-abliterated:F16
```

Lemonade

How to use Testament200156/old-MakeGemma3-abliterated with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Testament200156/old-MakeGemma3-abliterated:F16

Run and chat with the model

lemonade run user.old-MakeGemma3-abliterated-F16

List all available models

lemonade list

Atomic Chat

old-MakeGemma3

Note: multilingual feature improvement version has been posted. Please use Testament200156/MakeGemma3-abliterated. This location is currently deprecated. This is a merge of pre-trained language models created using mergekit. I have created a GGUF, so please check the GGUF folder. Since this is an experimental model, there are some defects, mainly in the multilingual functionality. Please use with caution.

Merge Details

Merge Method

This model was merged using the NuSLERP merge method.

Models Merged

The following models were included in the merge:

drwlf/medgemma-27b-it-abliterated
test_base (summykai/gemma3-27b-abliterated-dpo with additional layers added)

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: test_base
    parameters:
      weight: 1.0
  - model: medgemma-27b-it-abliterated
    parameters: 
      weight: 1.0
merge_method: nuslerp
dtype: bfloat16

Downloads last month: 9

Safetensors

Model size

29B params

Tensor type

BF16

Inference Providers NEW

Image-Text-to-Text

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