Instructions to use splash-team/SPLASH_3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use splash-team/SPLASH_3B with Transformers:

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

pipe = pipeline("image-text-to-text", model="splash-team/SPLASH_3B")
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("splash-team/SPLASH_3B")
model = AutoModelForMultimodalLM.from_pretrained("splash-team/SPLASH_3B", 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 splash-team/SPLASH_3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "splash-team/SPLASH_3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "splash-team/SPLASH_3B",
		"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/splash-team/SPLASH_3B

SGLang

How to use splash-team/SPLASH_3B 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 "splash-team/SPLASH_3B" \
    --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": "splash-team/SPLASH_3B",
		"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 "splash-team/SPLASH_3B" \
        --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": "splash-team/SPLASH_3B",
		"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 splash-team/SPLASH_3B with Docker Model Runner:
```
docker model run hf.co/splash-team/SPLASH_3B
```

nielsr HF Staff commited on Jul 10

Commit

4afc87a

verified ·

1 Parent(s): 4d153f4

Add model card for SPLASH-3B

Browse files

This PR adds a model card for SPLASH-3B to document the artifact and link it to the paper [Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs](https://huggingface.co/papers/2607.00302). It also configures the metadata with the appropriate `pipeline_tag` and `library_name`.

Files changed (1) hide show

README.md +25 -0

README.md ADDED Viewed

	@@ -0,0 +1,25 @@

+---
+library_name: transformers
+pipeline_tag: image-text-to-text
+---
+# SPLASH-3B: Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs
+**SPLASH-3B** is a tactile-aligned Multimodal Large Language Model (MLLM) based on the Qwen2.5-VL-3B-Instruct backbone. It integrates tactile perception into vision-language models using mask-isolated tactile alignment learning, allowing tactile reasoning while preserving general visual-language capabilities.
+- **Paper:** [Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs](https://huggingface.co/papers/2607.00302)
+- **Repository:** [ewha-mmai/splash](https://github.com/ewha-mmai/splash)
+- **Project Page:** [SPLASH Project Page](https://ewha-mmai.github.io/splash/)
+## Citation
+If you find SPLASH useful, please consider citing the paper:
+```bibtex
+@inproceedings{park2026splash,
+  title={Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs},
+  author={Yoonhyung Park and Minji Kim and Sungwon Moon and Jiyoung Lee},
+  booktitle={European Conference on Computer Vision (ECCV)},
+  year={2026}
+}
+```