Instructions to use docling-project/SmolDocling-256M-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use docling-project/SmolDocling-256M-preview with Transformers:

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

pipe = pipeline("image-text-to-text", model="docling-project/SmolDocling-256M-preview")
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("docling-project/SmolDocling-256M-preview")
model = AutoModelForImageTextToText.from_pretrained("docling-project/SmolDocling-256M-preview")
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 docling-project/SmolDocling-256M-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "docling-project/SmolDocling-256M-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "docling-project/SmolDocling-256M-preview",
		"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/docling-project/SmolDocling-256M-preview

SGLang

How to use docling-project/SmolDocling-256M-preview 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 "docling-project/SmolDocling-256M-preview" \
    --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": "docling-project/SmolDocling-256M-preview",
		"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 "docling-project/SmolDocling-256M-preview" \
        --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": "docling-project/SmolDocling-256M-preview",
		"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 docling-project/SmolDocling-256M-preview with Docker Model Runner:
```
docker model run hf.co/docling-project/SmolDocling-256M-preview
```

Layout detection mode?

#25

by prudant - opened Mar 22, 2025

Discussion

prudant

Mar 22, 2025

•

edited Mar 22, 2025

Can be used only to extract bboxes with layouts labels? and no text, i mean use the model for layout detection ?

prudant

Mar 25, 2025

u_u

reix2098

Mar 27, 2025

Hello Prudant,

It seems their intention is to integrate this model with the LayoutDetector as part of their broader project called Docling. While exploring their repositories, I came across docling-ibm-models, which I believe will eventually be merged into the main project, allowing us to extract text and categorize the layout labels at the same time.

In that repository, you can find an example demonstrating how to detect the layout of a page (bounding boxes with layout labels) without extracting text. The usage is straightforward:

python -m demo.demo_layout_predictor -i <input_dir> -v <viz_dir>

auerchristoph

Docling org Mar 27, 2025

•

edited Mar 27, 2025

Hello,
The SmolDocling model is already integrated in the docling project, please check our updated README. SmolDocling can be used as an alternative conversion path, which replaces all the other specific models we have in docling's standard pipeline. Using SmolDocling for layout analysis is possible but currently it won't be efficient for that, since the content is always produced as well. Training SmolDocling to output purely the structure tokens (including location) through a different query is part of our future plans and experimentation.

prudant

Mar 27, 2025

Thanks!

prudant changed discussion status to closed Mar 27, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment