rednote-hilab / dots.ocr-1.5

Introduction

We present dots.ocr-1.5 , a 3B-parameter multimodal model composed of a 1.2B vision encoder and a 1.7B language model. Designed for universal accessibility, it possesses the capability to recognize virtually any human script. Beyond achieving state-of-the-art (SOTA) performance in standard multilingual document parsing among models of comparable size, dots.ocr-1.5 excels at converting structured graphics (e.g., charts and diagrams) directly into SVG code, parsing web screens and spotting scene text. Furthermore, the model demonstrates competitive performance in general OCR, object grounding & counting tasks.

1. Stronger Document Parsing Performance: dots.ocr-1.5 maintains SOTA performance among latest OCR models, particularly on multilingual documents . Addressing the significant bias inherent in the detection & matching rules of certain benchmarks —which often fail to accurately reflect a model's true capabilities—we adopted an Elo score evaluation system. Under this metric, the performance landscape shifts significantly, highlighting the superior robustness of our model compared to conventional rankings.
2. Unified Vision-Language Parsing : Visual languages (e.g., charts, graphics, chemical formulas, logos) encapsulate dense human knowledge, akin to natural language. dots.ocr-1.5 unifies the interpretation of these elements by parsing them directly into SVG code. We have validated the effectiveness of this approach, demonstrating impressive results in structural and semantic recognition.
3. Broader and More General Capabilities : Compared to dots.ocr, dots.ocr-1.5 supports a significantly wider array of tasks. It extends beyond standard OCR to handle web screen parsing, scene text spotting, object grounding & counting, and other general OCR QA tasks.

Evaluation

1. Document Parsing

1.1 Elo Score of different bench between latest models

Notes:

• Results for Gemini 3 Pro, PaddleOCR-VL-1.5, and GLM-OCR were obtained via APIs, while HuanyuanOCR results were generated using local inference.
• The Elo score evaluation was conducted using Gemini 3 Flash. The prompt can be found at: Elo Score Prompt . These results are consistent with the findings on ocrarena .

1.2 olmOCR-bench

Note:

• The metrics are from olmocr , and our own internal evaluations.
• We delete the Page-header and Page-footer cells in the result markdown.

1.3 Other Benchmarks

Note:

• Metrics are sourced from OmniDocBench and other model publications. pdf-parse-bench results are reproduced by Qwen3-VL-235B-A22B-Instruct.
• Formula and Table metrics for OmniDocBench1.5 are omitted due to their high sensitivity to detection and matching protocols.

2. Vision-Language Parsing

Visual languages (e.g., charts, graphics, chemical formulas, logos) encapsulate dense human knowledge. dots.ocr-1.5 unifies the interpretation of these elements by parsing them directly into SVG code .

Note:

• We use the ISVGEN metric from UniSVG to evaluate the parsing result. For benchmarks that do not natively support image parsing, we use the original images as input, and calculate the ISVGEN score between the rendered output and the original image.
• OCRVerse results are derived from various code formats (e.g., SVG, Python), whereas results for Gemini 3 Pro and dots.ocr-1.5 are based specifically on SVG code.
• Due to the capacity constraints of a 3B-parameter VLM, dots.ocr-1.5 may not excel in all tasks yet like svg. To complement this, we are simultaneously releasing dots.ocr-1.5-svg. We plan to further address these limitations in future updates.

3. General Vision Tasks

Quick Start

1. Installation

Install dots.ocr-1.5

conda create -n dots_ocr python=3.12
conda activate dots_ocr

git clone https://github.com/rednote-hilab/dots.ocr.git
cd dots.ocr

# Install pytorch, see https://pytorch.org/get-started/previous-versions/ for your cuda version
pip install torch==2.7.0 torchvision==0.22.0 torchaudio==2.7.0 --index-url https://download.pytorch.org/whl/cu128
pip install -e .

If you have trouble with the installation, try our Docker Image for an easier setup, and follow these steps:

git clone https://github.com/rednote-hilab/dots.ocr.git
cd dots.ocr
pip install -e .

Download Model Weights

💡 Note: Please use a directory name without periods (e.g., DotsOCR_1_5 instead of dots.ocr-1.5 ) for the model save path. This is a temporary workaround pending our integration with Transformers.

python3 tools/download_model.py

2. Deployment

vLLM inference

We highly recommend using vllm for deployment and inference.

# launch vllm server
## dots.ocr-1.5
CUDA_VISIBLE_DEVICES=0 vllm serve rednote-hilab/dots.ocr-1.5 --tensor-parallel-size 1 --gpu-memory-utilization 0.9 --chat-template-content-format string --served-model-name model --trust-remote-code

## dots.ocr-1.5-svg
CUDA_VISIBLE_DEVICES=0 vllm serve rednote-hilab/dots.ocr-1.5-svg --tensor-parallel-size 1 --gpu-memory-utilization 0.9 --chat-template-content-format string --served-model-name model --trust-remote-code

# vllm api demo
## document parsing
python3 ./demo/demo_vllm.py --prompt_mode prompt_layout_all_en
## web parsing 
python3 ./demo/demo_vllm.py --prompt_mode prompt_web_parsing --image_path ./assets/showcase_dots_ocr_1_5/origin/webpage_1.png
## scene spoting
python3 ./demo/demo_vllm.py --prompt_mode prompt_scene_spotting --image_path ./assets/showcase_dots_ocr_1_5/origin/scene_1.jpg
## image parsing with svg code
python3 ./demo/demo_vllm_svg.py --prompt_mode prompt_image_to_svg 
## general qa
python3 ./demo/demo_vllm_general.py

Hugginface inference

python3 demo/demo_hf.py

import torch
from transformers import AutoModelForCausalLM, AutoProcessor, AutoTokenizer
from qwen_vl_utils import process_vision_info
from dots_ocr.utils import dict_promptmode_to_prompt

model_path = "./weights/DotsOCR_1_5"
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    attn_implementation="flash_attention_2",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)

image_path = "demo/demo_image1.jpg"
prompt = """Please output the layout information from the PDF image, including each layout element's bbox, its category, and the corresponding text content within the bbox.

1. Bbox format: [x1, y1, x2, y2]

2. Layout Categories: The possible categories are ['Caption', 'Footnote', 'Formula', 'List-item', 'Page-footer', 'Page-header', 'Picture', 'Section-header', 'Table', 'Text', 'Title'].

3. Text Extraction & Formatting Rules:
    - Picture: For the 'Picture' category, the text field should be omitted.
    - Formula: Format its text as LaTeX.
    - Table: Format its text as HTML.
    - All Others (Text, Title, etc.): Format their text as Markdown.

4. Constraints:
    - The output text must be the original text from the image, with no translation.
    - All layout elements must be sorted according to human reading order.

5. Final Output: The entire output must be a single JSON object.
"""

messages = [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image_path
                },
                {"type": "text", "text": prompt}
            ]
        }
    ]

# Preparation for inference
text = processor.apply_chat_template(
    messages, 
    tokenize=False, 
    add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)

inputs = inputs.to("cuda")

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=24000)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

3. Document Parse

Based on vLLM server , you can parse an image or a pdf file using the following commands:

# Parse all layout info, both detection and recognition
# Parse a single image
python3 dots_ocr/parser.py demo/demo_image1.jpg
# Parse a single PDF
python3 dots_ocr/parser.py demo/demo_pdf1.pdf  --num_thread 64  # try bigger num_threads for pdf with a large number of pages

# Layout detection only
python3 dots_ocr/parser.py demo/demo_image1.jpg --prompt prompt_layout_only_en

# Parse text only, except Page-header and Page-footer
python3 dots_ocr/parser.py demo/demo_image1.jpg --prompt prompt_ocr

4. Demo

Have fun with the live demo .

Examples for document parsing

Examples for image parsing

Note:

• Inferenced by dots.ocr-1.5-svg

Example for web parsing

Examples for scene spotting

Limitation & Future Work

• Complex Document Elements:

  • Table&Formula : The extraction of complex tables and mathematical formulas persists as a difficult task given the model's compact architecture.
  • Picture : We have adopted an SVG code representation for parsing structured graphics; however, the performance has yet to achieve the desired level of robustness.

• Parsing Failures: While we have reduced the rate of parsing failures compared to the previous version, these issues may still occur occasionally. We remain committed to further resolving these edge cases in future updates.