Instructions to use FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari with Transformers:

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

pipe = pipeline("image-text-to-text", model="FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari")
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("FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari")
model = AutoModelForImageTextToText.from_pretrained("FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari")
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 FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari",
		"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/FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari

SGLang

How to use FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari 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 "FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari" \
    --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": "FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari",
		"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 "FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari" \
        --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": "FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari",
		"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 FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari with Docker Model Runner:
```
docker model run hf.co/FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari
```

Waraqon v3: Arabic OCR with HTML Structure

Fine-tuned Qwen2-VL model for Arabic OCR with HTML formatting, trained on Qari 0.3 dataset.

Model Details

Base Model: NAMAA-Space/Qari-OCR-0.2.2.1-VL-2B-Instruct
Training Dataset: QariOCR-v0.3-markdown-mixed-dataset
Training Steps: 5,000 (checkpoint from interruption)
Fine-tuning Method: LoRA with Unsloth

Usage

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
from PIL import Image
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari",
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True
)
processor = AutoProcessor.from_pretrained("FatimahEmadEldin/Waraqon-v3-Arabic-OCR-HTML-Qari", trust_remote_code=True)

image = Image.open("arabic_text.jpg")
messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": image},
        {"type": "text", "text": "استخرج النص من هذه الصورة بتنسيق HTML"}
    ]
}]

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").to(model.device)

with torch.no_grad():
    output_ids = model.generate(**inputs, max_new_tokens=2048)

generated_ids = [output_ids[len(input_ids):] 
                 for input_ids, output_ids in zip(inputs.input_ids, output_ids)]
output = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(output)