# Document VLM FT: DocVQA + ChartQA + TableVQA + Turkish Invoice/Petition Dataset

> Source: https://sukruyusufkaya.com/en/learn/fine-tuning-cookbook/ftc-document-vlm-docvqa-chartqa-tr
> Updated: 2026-05-14T14:42:54.432Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part VI — Vision-Language Multimodal FT
**TLDR:** Document AI use-cases: DocVQA, ChartQA, TableVQA. TR-specific dataset generation: synthetic invoice + petition + contract images, structured field extraction. Qwen 2.5-VL 7B baseline → FT → field accuracy 76% → 94%.