update citation, add image, tags, and changed pipeline

README.md

@@ -6,6 +6,7 @@ tags:
 - unsloth
 - qwen2_vl
 - trl
+- ocr
 license: apache-2.0
 language:
 - ar
@@ -13,13 +14,20 @@ metrics:
 - bleu
 - wer
 - cer
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 
 # Qari-OCR-0.1-VL-2B-Instruct Model
 
 ## Model Overview
+
 This model is a fine-tuned version of [unsloth/Qwen2-VL-2B-Instruct](unsloth/Qwen2-VL-2B-Instruct-unsloth-bnb-4bit) on an Arabic OCR dataset. It is optimized to perform Arabic Optical Character Recognition (OCR) for full-page text.
 
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/628f7a71dd993507cfcbe587/HuUcfziXcDT_2kwDoz5qH.png)
+
+
 ## Model Details
 - **Base Model**: Qwen2 VL
 - **Fine-tuning Dataset**: Arabic OCR dataset
@@ -128,4 +136,16 @@ print(output_text)
 This model follows the licensing terms of the original Qwen2 VL model. Please review the terms before using it commercially.
 
 ## Citation
-If you use this model in your research or application, please cite it appropriately.
+
+If you use this model in your research, please cite:
+
+```
+@misc{QariOCR2025,
+  title={Qari-OCR: A High-Accuracy Model for Arabic Optical Character Recognition},
+  author={NAMAA},
+  year={2025},
+  publisher={Hugging Face},
+  howpublished={\url{https://huggingface.co/NAMAA-Space/Qari-OCR-0.1-VL-2B-Instruct}},
+  note={Accessed: 2025-03-03}
+}
+```