Instructions to use ngxson/tinygemma3_cifar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ngxson/tinygemma3_cifar with Transformers:

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

pipe = pipeline("image-text-to-text", model="ngxson/tinygemma3_cifar")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("ngxson/tinygemma3_cifar")
model = AutoModelForImageTextToText.from_pretrained("ngxson/tinygemma3_cifar")
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

vLLM

How to use ngxson/tinygemma3_cifar with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ngxson/tinygemma3_cifar"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ngxson/tinygemma3_cifar",
		"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/ngxson/tinygemma3_cifar

SGLang

How to use ngxson/tinygemma3_cifar 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 "ngxson/tinygemma3_cifar" \
    --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": "ngxson/tinygemma3_cifar",
		"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 "ngxson/tinygemma3_cifar" \
        --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": "ngxson/tinygemma3_cifar",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use ngxson/tinygemma3_cifar with Docker Model Runner:
```
docker model run hf.co/ngxson/tinygemma3_cifar
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

tinygemma3 with vision

This is trained on CIFAR-10 dataset.

How to use:

from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "ngxson/tinygemma3_cifar"

model = AutoModelForImageTextToText.from_pretrained(model_id).to("cuda")
processor = AutoProcessor.from_pretrained(model_id)


#####################

from datasets import load_dataset, Dataset

ds_full = load_dataset("uoft-cs/cifar10")

def ex_to_msg(ex):
    txt = [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What is this:"},
                {"type": "image"}
            ]
        }
    ]
    img = ex["img"]
    return {
        "messages": txt,
        "images": [img],
    }


#####################

test_idx = 0

test_msg = ex_to_msg(ds_full["train"][test_idx])

test_txt = processor.apply_chat_template(test_msg["messages"], tokenize=False, add_generation_prompt=True)
test_input = processor(text=test_txt, images=test_msg["images"], return_tensors="pt").to(model.device)

#####################

generated_ids = model.generate(**test_input, do_sample=False, max_new_tokens=1)
generated_texts = processor.batch_decode(
    generated_ids,
    skip_special_tokens=True,
)
print(generated_texts)

# expected answer for test_idx = 0 is "airplane"

Downloads last month: 3

Safetensors

Model size

39.3M params

Tensor type

F32

Model tree for ngxson/tinygemma3_cifar

Quantizations

1 model