Arabic OCR DeepSeek OCR 2

--- license: apache-2.0 language: - en - ar library_name: transformers tags: - unsloth - deepseek - deepseek-ocr - arabic - ocr - vision - text-extraction - merged - lora pipeline_tag: image-to-text base_model: unsloth/DeepSeek-OCR-2 --- # Arabic-OCR-DeepSeek-OCR-2-3B This repository contains the `bfloat16` merged version of the DeepSeek-OCR-2 (3B) Model, fine-tuned by **loay** for the specific task of performing high-precision Optical Character Recognition (OCR) and structural layout analysis on Arabic text from images. The model was created by fine-tuning the `unsloth/DeepSeek-OCR-2` model using LoRA adapters. The high-performance training was made possible by the **Unsloth** library, and the adapters were then merged back into the base model for easy deployment. ## Model Details - **Fine-tuned by:** [loay](https://huggingface.co/loay) - **Base Model:** `unsloth/DeepSeek-OCR-2` - **Fine-tuning Task:** Arabic Optical Character Recognition, specialized for the **"Free OCR"** instruction. - **Training Data:** The model was trained on a high-quality dataset of 35,921 images of real Arabic scanned books and their corresponding structured transcriptions, generated using Gemini 2 Flash. - **Hardware & Performance:** Training was conducted on an NVIDIA H100 (80GB VRAM) leveraging native `bfloat16` precision and Flash Attention 2 for optimal quality and speed. - **LoRA Configuration:** High-capacity adaptation was achieved using a rank of `r=64` and `lora_alpha=128`. The targeted modules include `["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"]`. - **Vision Strategy:** The model utilizes high-resolution dynamic multi-patch cropping (`crop_mode=True`) to handle varying large page sizes correctly without downscaling text artifacts. - **Output Format:** This is a native `bfloat16` precision model.

Source context: 39 downloads · 0 likes · Pipeline image-to-text · Library transformers · Repo loay/Arabic-OCR-DeepSeek-OCR-2