LightOnOCR-1B-1025

uv venv --python 3.12 --seed
source .venv/bin/activate

# install any version higher than 0.11.1
uv pip install vllm==0.11.2
# extra deps need only to run the example below
uv pip install pypdfium2 pillow requests

vllm serve lightonai/LightOnOCR-1B-1025 \
    --limit-mm-per-prompt '{"image": 1}' --mm-processor-cache-gb 0 --no-enable-prefix-caching

import base64
import requests
import pypdfium2 as pdfium
import io

ENDPOINT = "http://localhost:8000/v1/chat/completions"
MODEL = "lightonai/LightOnOCR-1B-1025"

# Download PDF from arXiv
pdf_url = "https://arxiv.org/pdf/2412.13663"
pdf_data = requests.get(pdf_url).content

# Open PDF and convert first page to image
pdf = pdfium.PdfDocument(pdf_data)
page = pdf[0]
# Render at 200 DPI (scale factor = 200/72 ≈ 2.77)
pil_image = page.render(scale=2.77).to_pil()

# Convert to base64
buffer = io.BytesIO()
pil_image.save(buffer, format="PNG")
image_base64 = base64.b64encode(buffer.getvalue()).decode('utf-8')

# Make request
payload = {
    "model": MODEL,
    "messages": [{
        "role": "user",
        "content": [{
            "type": "image_url",
            "image_url": {"url": f"data:image/png;base64,{image_base64}"}
        }]
    }],
    "max_tokens": 4096,
    "temperature": 0.2,
    "top_p": 0.9,
}

response = requests.post(ENDPOINT, json=payload)
text = response.json()['choices'][0]['message']['content']
print(text)

uv pip install git+https://github.com/huggingface/transformers

import torch
from transformers import LightOnOcrForConditionalGeneration, LightOnOcrProcessor

device = "mps" if torch.backends.mps.is_available() else "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float32 if device == "mps" else torch.bfloat16

model = LightOnOcrForConditionalGeneration.from_pretrained("lightonai/LightOnOCR-2-1B-base", torch_dtype=dtype).to(device)
processor = LightOnOcrProcessor.from_pretrained("lightonai/LightOnOCR-2-1B-base")

url = "https://huggingface.co/datasets/hf-internal-testing/fixtures_ocr/resolve/main/SROIE-receipt.jpeg"
conversation = [{"role": "user", "content": [{"type": "image", "url": url}]}]

inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
)
inputs = {k: v.to(device=device, dtype=dtype) if v.is_floating_point() else v.to(device) for k, v in inputs.items()}

output_ids = model.generate(**inputs, max_new_tokens=1024)
generated_ids = output_ids[0, inputs["input_ids"].shape[1]:]
output_text = processor.decode(generated_ids, skip_special_tokens=True)
print(output_text)

@misc{lightonocr2025,
  title        = {LightOnOCR-1B: End-to-End and Efficient Domain-Specific Vision-Language Models for OCR},
  author       = {Said Taghadouini and Baptiste Aubertin and Adrien Cavaillès},
  year         = {2025},
  howpublished = {\url{https://huggingface.co/blog/lightonai/lightonocr}}
}