Instructions to use winninghealth/WiNGPT-DocLoom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use winninghealth/WiNGPT-DocLoom with Transformers:

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

pipe = pipeline("image-text-to-text", model="winninghealth/WiNGPT-DocLoom")
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("winninghealth/WiNGPT-DocLoom")
model = AutoModelForImageTextToText.from_pretrained("winninghealth/WiNGPT-DocLoom")
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 winninghealth/WiNGPT-DocLoom with vLLM:

Install from pip and serve model

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

SGLang

How to use winninghealth/WiNGPT-DocLoom 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 "winninghealth/WiNGPT-DocLoom" \
    --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": "winninghealth/WiNGPT-DocLoom",
		"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 "winninghealth/WiNGPT-DocLoom" \
        --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": "winninghealth/WiNGPT-DocLoom",
		"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 winninghealth/WiNGPT-DocLoom with Docker Model Runner:
```
docker model run hf.co/winninghealth/WiNGPT-DocLoom
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DocLoom

Performance Comparison of Various Models on the olmOCR-Bench Dataset

OCR Model Performance Table

		Arxiv	Old scans math	Tables	Old scans	Headers and footers	Multi columnn	Long tiny text	Base	Overall
Marker 1.10.1	--	83.8	66.8	72.9	33.5	86.6	80	85.7	99.3	76.1±1.1
MinerU 2.5.4	--	76.6	54.6	84.9	33.7	96.6	78.2	83.5	93.7	75.2±1.1
DeepSeek-OCR	--	77.2	73.6	80.2	33.3	96.1	66.4	79.4	99.8	75.7±1.0
Nanonts-OCR2-3B	3B	75.4	46.1	86.8	40.9	32.1	81.9	93	99.6	69.5±1.1
Mistral OCR	--	77.2	67.5	60.6	29.3	93.6	71.3	77.1	99.4	72.0±1.1
MonkeyOCR-pro-3B	3B	83.8	68.8	74.6	36.1	91.2	76.6	80.1	95.3	75.8±1.0
Qwen3-VL-4B-Instruct	4B	83.1	74.5	83.9	40.5	35.5	81.7	88.7	99.3	73.4±1.0
olmOCR pipeline v0.4.0 with olmOCR-2-7B-1025	7B	82.9	82.1	84.3	48.3	95.7	84.3	81.4	99.7	82.3±1.1
DocLoom	4B	74.3	66.6	80.9	45.1	91.4	82.9	89.1	99.7	78.8±1.0

Introduction

DocLoom is dedicated to structured text extraction from complex PDFs. Its core goal is to convert unstructured PDF content into linearly organized plain text in natural reading order, while accurately preserving key structural information (e.g., chapter hierarchies, tables, lists, formulas) to provide high-quality data for downstream tasks such as document parsing, information retrieval, and data mining.

Based on the Qwen3-VL-4B-Instruct architecture, improve the special adaptability of PDF processing through Supervised Fine-Tuning (SFT).
Adopt "existing data + synthetic data" dual-source training, with a focus on enhancing the performance of PDF processing in the medical field.
On olmOCR-Bench , compared with other models of the same parameter scale, WiNGPT-OCR-4B has achieved excellent performance.

How to Use

Transformers (Recommended)

Refer to Qwen3-VL-4B-Instruct for guidance on model inference acceleration and PDF processing, etc.

vLLM (Recommended)

For high-performance inference and deployment, we recommend using vLLM. We also provide a standalone script for efficiently processing multi-page PDF documents. This script operates independently and does not require the official olmOCR toolkit, offering a lightweight and fast way to perform OCR on entire documents.

python DocLoom_test.py <pdf_file_path>

Acknowledgement

We express our gratitude to the teams that developed olmOCR and Qwen3-VL, which were instrumental in our research.

Downloads last month: 14

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for winninghealth/WiNGPT-DocLoom

Base model

Qwen/Qwen3-VL-4B-Instruct

Finetuned

(273)

this model

Quantizations

2 models