---
base_model:
- Qwen/Qwen3-VL-2B-Instruct
tags:
- text-generation-inference
- transformers
- qwen3_vl
- ocr
- Optical Character Recognition
- vision-language
license: apache-2.0
language:
- en
- ar
- fa
datasets:
- mohajesmaeili/Persian_Arabic_TextLine_Image_Ocr_Small
pipeline_tag: image-to-text
---