Instructions to use docling-project/SmolDocling-256M-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
ValueError: Model architectures ['Idefics3ForConditionalGeneration'] failed to be inspected. Please check the logs for more details.
How can I fix this issue?
How can I replicate this error any tips? Are you sure you are on the latest transformers version?
Below is the code to reproduce it. I am actually on the 4.50.0 dev version
import time
import os
from vllm import LLM, SamplingParams
from PIL import Image
from docling_core.types.doc import DoclingDocument
from docling_core.types.doc.document import DocTagsDocument
MODEL_PATH = "ds4sd/SmolDocling-256M-preview"
IMAGE_DIR = "img/" # Place your page images here
OUTPUT_DIR = "out_docling/"
PROMPT_TEXT = "Convert page to Docling."
os.makedirs(OUTPUT_DIR, exist_ok=True)
llm = LLM(model=MODEL_PATH, limit_mm_per_prompt = {'image': 1})
sampling_params = SamplingParams(
temperature = 0.0,
max_tokens = 8192
)
chat_template = f"<|im_start|>User:{PROMPT_TEXT}Assistant:"
image_files= ["example_data/Images/0194b1c3-a881-7062-a861-e1bb66bb75d6_4.png"]
start_time = time.time()
total_tokens = 0
images = [Image.open(image_file) for image_file in image_files]
llm_input = [{'prompt': chat_template, 'multi_modal_data': {'image': image}} for image in images]
outputs = llm.generate([llm_input], sampling_params=sampling_params)
print(f"Total time: {time.time() - start_time:.2f} sec")
for output, img_file in zip(outputs,image_files):
doctags = output.outputs[0].text
image = Image.open(img_file)
img_fn = os.path.splittext(img_file)[0]
output_filename =img_fn + ".dt"
output_path = os.path.join(OUTPUT_DIR, output_filename)
with open(output_path, "w", encoding="utf-8") as f:
f.write(doctags)
doctags_doc = DocTagsDocument.from_doctags_and_image_pairs([doctags], [image])
doc = DoclingDocument(name='Document')
doc.load_from_doctags(doctags_doc)
output_filename_md = img_fn + '.md'
output_path_md = os.path.join(OUTPUT_DIR, output_filename_md)
doc.save_as_markdown(output_path_md)
output_filename_md = img_fn + '.xml'
output_path_md = os.path.join(OUTPUT_DIR, output_filename_md)
doc.save_as_xml(output_path_md)