supergemma4-26b-abliterated-multimodal

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

Libraries

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

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

pipe = pipeline("text-generation", model="eadx/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("eadx/supergemma4-26b-abliterated-multimodal")
model = AutoModelForMultimodalLM.from_pretrained("eadx/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 eadx/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 "eadx/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": "eadx/supergemma4-26b-abliterated-multimodal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

Docker Model Runner
How to use eadx/supergemma4-26b-abliterated-multimodal with Docker Model Runner:
```
docker model run hf.co/eadx/supergemma4-26b-abliterated-multimodal
```

supergemma4-26b-abliterated-multimodal / SERVING_NOTES.md

eadx

Duplicate from Jiunsong/supergemma4-26b-abliterated-multimodal

dd26c25 about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.14 kB

	# Serving Notes

	This release uses the official Hugging Face Gemma 4 checkpoint naming/layout.
	The bundled `chat_template.jinja` and the inline template in
	`tokenizer_config.json` were refreshed together on April 18, 2026 and should
	be kept in sync if you make further prompt-template edits.

	## vLLM

	Gemma 4 multi-turn tool use is sensitive to the chat template and reasoning parser.
	The vLLM fix set merged on April 8, 2026 in PR #39027 documents the working setup:

	`vllm serve google/gemma-4-31B-it --tool-call-parser gemma4 --enable-auto-tool-choice --reasoning-parser gemma4 --default-chat-template-kwargs '{"enable_thinking": true}' --chat-template examples/tool_chat_template_gemma4.jinja`

	Reference:
	https://github.com/vllm-project/vllm/pull/39027

	For plain chat serving, keep reasoning disabled by default unless you
	explicitly want reasoning content in responses. Gemma 4 templates can emit
	reasoning channel markers, so validate your final serving config against the
	exact chat template bundled in this release.

	## SGLang

	SGLang's OpenAI-compatible server uses the Hugging Face tokenizer chat
	template by default. If you need a different template, launch with
	`--chat-template /path/to/template.jinja`. If the tokenizer exposes multiple
	named templates, you can select one with `--hf-chat-template-name`.

	Reference:
	https://docs.sglang.io/references/custom_chat_template.html
	https://docs.sglang.io/advanced_features/server_arguments.html

	## Apple Silicon / MLX

	TurboQuant+ is an inference-time optimization, not a weight change. It can be used
	with MLX-compatible Gemma 4 models to improve long-context KV-cache efficiency.

	Reference:
	https://github.com/TheTom/turboquant_plus

	## Validation

	Latest local validation on April 18, 2026:

	- Capability audit: 9 / 9 passed
	- Reliability audit: 20 / 20 passed
	- Local OpenAI-compatible MLX red-team: 10 / 13 passed

	The remaining MLX red-team misses were caused by 2 strict checker phrase mismatches
	on safe refusals and 1 text-only multimodal rejection mismatch. They did not surface
	as hidden-prompt leakage, loop regressions, or truthfulness regressions in the final run.