Model Card: Qwen2.5-VL-7B OCR Fine-Tuned (Arabic + English)
Model Summary
This model is a fine-tuned version of unsloth/Qwen2.5-VL-7B-Instruct-GGUF designed for OCR (Optical Character Recognition) on Arabic and English text.
It is trained using the QariOCR v0.3 mixed dataset and optimized for transcribing scanned documents, handwritten text, and mixed Arabic-English inputs.
Intended Use
- Primary use case: Accurate OCR for Arabic & English text, including diacritics and punctuation.
- Examples:
- Scanned books, articles, and religious texts.
- Handwritten forms and mixed-language documents.
- Academic digitization projects.
Training Data
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for mo1998/arabic-ocr-qwen2.5-vl
Base model
Qwen/Qwen2.5-VL-7B-Instruct Quantized
unsloth/Qwen2.5-VL-7B-Instruct-GGUF