Instructions to use Jiunsong/supergemma4-26b-abliterated-multimodal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jiunsong/supergemma4-26b-abliterated-multimodal with Transformers:

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

pipe = pipeline("text-generation", model="Jiunsong/supergemma4-26b-abliterated-multimodal")
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("Jiunsong/supergemma4-26b-abliterated-multimodal")
model = AutoModelForMultimodalLM.from_pretrained("Jiunsong/supergemma4-26b-abliterated-multimodal")
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 Jiunsong/supergemma4-26b-abliterated-multimodal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jiunsong/supergemma4-26b-abliterated-multimodal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jiunsong/supergemma4-26b-abliterated-multimodal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jiunsong/supergemma4-26b-abliterated-multimodal

SGLang

How to use Jiunsong/supergemma4-26b-abliterated-multimodal 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 "Jiunsong/supergemma4-26b-abliterated-multimodal" \
    --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": "Jiunsong/supergemma4-26b-abliterated-multimodal",
		"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 "Jiunsong/supergemma4-26b-abliterated-multimodal" \
        --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": "Jiunsong/supergemma4-26b-abliterated-multimodal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jiunsong/supergemma4-26b-abliterated-multimodal with Docker Model Runner:
```
docker model run hf.co/Jiunsong/supergemma4-26b-abliterated-multimodal
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SuperGemma4-26b-abliterated-multimodal

BF16 Gemma 4 multimodal release with an April 18 stability refresh focused on truthfulness, exact JSON/tool-call formatting, long-context extraction, loop resistance, and cleaner prompt hygiene.

April 18 Stability Refresh

Synced the external chat_template.jinja and inline tokenizer_config.json template so local and hosted runtimes read the same prompt rules.
Hardened false-premise handling so the model corrects bad assumptions instead of continuing under them.
Tightened JSON-only and tool-call formatting so exact-key JSON and execute_code calls stay machine-parseable.
Improved long-context sentinel extraction behavior for retrieval-style prompts.
Reinforced identity and prompt-hygiene responses to avoid mixed-script glitches and hidden-tag leakage.

Validation Snapshot

Capability audit: 9 / 9 passed, 100.0%
Reliability audit: 20 / 20 passed, 100.0%
Server red-team: 10 / 13 passed on the local MLX OpenAI-compatible server
Remaining server misses were 2 semantic checker mismatches on safe refusals and 1 text-only multimodal rejection mismatch, not a truthfulness or leak regression.

Included Files

Official Hugging Face-format BF16 weights
chat_template.jinja
tool_chat_template.jinja for Gemma 4 tool-calling setups
SERVING_NOTES.md with Gemma 4 runtime notes for vLLM, SGLang, and MLX
BENCHMARK_SNAPSHOT.md with the current validation summary

Notes

Checkpoint keys were aligned to the official Gemma 4 Hugging Face naming/layout for portable serving.
tokenizer_config.json includes an inline chat_template for portability and should match chat_template.jinja.
For multi-turn tool use on vLLM, use the dedicated tool_chat_template.jinja and Gemma 4 parser settings from SERVING_NOTES.md.

Downloads last month: 360

Safetensors

Model size

26B params

Tensor type

BF16

Model tree for Jiunsong/supergemma4-26b-abliterated-multimodal

Finetunes

1 model

Quantizations

11 models