Qari-OCR-LoRA

import torch
from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from peft import PeftModel
from PIL import Image

# Load base model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)
 
# Load LoRA adapter
model = PeftModel.from_pretrained(model, "HassanB4/Qari-OCR-LoRA")
model.eval()

# Load processor
processor = AutoProcessor.from_pretrained(
    "NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct",
    trust_remote_code=True
)

# Example inference
image = Image.open("manuscript_line.png").convert("RGB")

messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": image},
        {"type": "text", "text": "Below is the image of one page of a document. Just return the plain text representation of this document as if you were reading it naturally. Do not hallucinate."}
    ]
}]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], return_tensors="pt")
inputs = {k: v.to(model.device) for k, v in inputs.items()}

with torch.no_grad():
    output_ids = model.generate(**inputs, max_new_tokens=512, do_sample=False)

transcription = processor.decode(output_ids[0][len(inputs['input_ids'][0]):], skip_special_tokens=True)
print(transcription)