LightOnOCR-1B-1025 API & Inference Endpoint

Model Overview

LightOnOCR combines a Vision Transformer encoder(Pixtral-based) with a lightweight text decoder(Qwen3-based) distilled from high-quality open VLMs. It is optimized for document parsing tasks, producing accurate, layout-aware text extraction from high-resolution pages.

Benchmarks

All benchmarks evaluated using vLLM on the Olmo-Bench.

Installation

VLLM

[2025/11/24] 🚀 LightOnOCR is now officially supported in vLLM v0.11.1 🚀

bash
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

Start Server

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

PDF Inference

python
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)

Transformers

Note: LightOnOCR-2 requires transformers installed from source (not yet in a stable release).

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

python
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)

Rendering and Preprocessing Tips

Render PDFs to PNG or JPEG at a target longest dimension of 1540px
Maintain aspect ratio to preserve text geometry
Use one image per page; batching supported by vLLM

Variants

Table with columns: Variant, Description
Variant	Description
LightOnOCR-1B-1025	Full multilingual model (default)
LightOnOCR-1B-32k	Fastest pruned-vocabulary version (32k tokens) optimized for European languages
LightOnOCR-1B-16k	Most compact variant with smallest vocabulary

Fine-tuning

Transformers integration is coming soon for training and inference.

LightOnOCR is fully differentiable and supports:

LoRA fine-tuning
Domain adaptation (receipts, scientific articles, forms, etc.)
Multilingual fine-tuning with task-specific corpora

📓 Finetuning notebook

Data

Trained on a diverse large-scale PDF corpus covering:

Scientific papers, books, receipts, invoices, tables, forms, and handwritten text
Multiple languages (Latin alphabet dominant)
Real and synthetic document scans

The dataset will be released under an open license.

License

Apache License 2.0

Acknowlegments

The project received funding from the BPI Scribe project.

Citation

markdown
@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}}
}

bash

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

python

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)

python

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)

Variant

Description

LightOnOCR-1B-1025

Full multilingual model (default)

LightOnOCR-1B-32k

Fastest pruned-vocabulary version (32k tokens) optimized for European languages

LightOnOCR-1B-16k

Most compact variant with smallest vocabulary

markdown

@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}}
}

LightOnOCR-1B-1025

README

Model Overview

Benchmarks

Installation

VLLM

Transformers

Rendering and Preprocessing Tips

Variants

Fine-tuning

Data

License

Acknowlegments

Citation

Explore FriendliAI today

README

Model Overview

Benchmarks

Installation

VLLM

Transformers

Rendering and Preprocessing Tips

Variants

Fine-tuning

Data

License

Acknowlegments

Citation