# Document VLM FT: DocVQA + ChartQA + TableVQA + Türkçe Fatura/Dilekçe Dataset

> Source: https://sukruyusufkaya.com/learn/fine-tuning-cookbook/ftc-document-vlm-docvqa-chartqa-tr
> Updated: 2026-08-20T15:28:43.597Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part VI — Vision-Language Multimodal FT
**TLDR:** Document AI use-case'leri: DocVQA (document Q&A), ChartQA (grafik anlama), TableVQA (tablo extraction). TR-spesifik dataset üretimi: synthetic fatura + dilekçe + sözleşme images, structured field extraction. Qwen 2.5-VL 7B baseline → FT → field accuracy %76 → %94.