Instructions to use WWTCyberLab/gemma-4-26B-A4B-it-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WWTCyberLab/gemma-4-26B-A4B-it-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="WWTCyberLab/gemma-4-26B-A4B-it-abliterated")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("WWTCyberLab/gemma-4-26B-A4B-it-abliterated")
model = AutoModelForMultimodalLM.from_pretrained("WWTCyberLab/gemma-4-26B-A4B-it-abliterated", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WWTCyberLab/gemma-4-26B-A4B-it-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WWTCyberLab/gemma-4-26B-A4B-it-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WWTCyberLab/gemma-4-26B-A4B-it-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WWTCyberLab/gemma-4-26B-A4B-it-abliterated

SGLang

How to use WWTCyberLab/gemma-4-26B-A4B-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 "WWTCyberLab/gemma-4-26B-A4B-it-abliterated" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WWTCyberLab/gemma-4-26B-A4B-it-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "WWTCyberLab/gemma-4-26B-A4B-it-abliterated" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WWTCyberLab/gemma-4-26B-A4B-it-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WWTCyberLab/gemma-4-26B-A4B-it-abliterated with Docker Model Runner:
```
docker model run hf.co/WWTCyberLab/gemma-4-26B-A4B-it-abliterated
```

jasonludwig commited on Apr 10

Commit

f7a2024

verified ·

1 Parent(s): 1bbc855

Final benchmarks: 2/48 hard refusal, MMLU 65.1% (+0.7%)

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -19,7 +19,8 @@ pipeline_tag: text-generation
 | Metric | Value |
 |--------|-------|
-| **Refusal Rate** | ~0% deterministic (stochastic hedging ~20% of runs at temp 0.4) |
 | **Quality (QPS)** | 107%+ |
 | **Elo Delta** | Positive (quality improved) |

 | Metric | Value |
 |--------|-------|
+| **Refusal Rate** | 4.2% hard refusal (2/48), 25% soft hedging (12/48) at temp 0.4 |
+| **MMLU** | 65.1% (5-shot), +0.7% vs original (64.4%) |
 | **Quality (QPS)** | 107%+ |
 | **Elo Delta** | Positive (quality improved) |