Instructions to use Robo420/gemma-3n-e4b-bratwurst with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Robo420/gemma-3n-e4b-bratwurst with Transformers:

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

pipe = pipeline("image-text-to-text", model="Robo420/gemma-3n-e4b-bratwurst")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Robo420/gemma-3n-e4b-bratwurst")
model = AutoModelForMultimodalLM.from_pretrained("Robo420/gemma-3n-e4b-bratwurst", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Robo420/gemma-3n-e4b-bratwurst with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Robo420/gemma-3n-e4b-bratwurst"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Robo420/gemma-3n-e4b-bratwurst",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Robo420/gemma-3n-e4b-bratwurst

SGLang

How to use Robo420/gemma-3n-e4b-bratwurst 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 "Robo420/gemma-3n-e4b-bratwurst" \
    --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": "Robo420/gemma-3n-e4b-bratwurst",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Robo420/gemma-3n-e4b-bratwurst" \
        --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": "Robo420/gemma-3n-e4b-bratwurst",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Robo420/gemma-3n-e4b-bratwurst with Docker Model Runner:
```
docker model run hf.co/Robo420/gemma-3n-e4b-bratwurst
```

Uploaded finetuned model

Developed by: Robo420
License: Gemma
Finetuned from model : unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit

This model was finetuned on a german dataset and should be better at staying coherent in german.

This gemma3n model was trained 2x faster with Unsloth and Huggingface's TRL library.

Notice: I still had to pay for Google Colab though, even if the unsloth finetune collab tells you it works in free mode, since it kept running OOM when generating the final weigths.

GGUF following as soon as i get around to do it.

Downloads last month: 8

Safetensors

Model size

8B params

Tensor type

BF16

F16

Robo420
/

gemma-3n-e4b-bratwurst

Uploaded finetuned model

Dataset used to train Robo420/gemma-3n-e4b-bratwurst