Vqa Python Packages

crystal-metrics

CRYSTAL: Beyond Final Answers: Benchmark for Transparent Multimodal Reasoning Evaluation | arXiv 2603.13099

tinydoc

Python SDK for TinyDoc-VLM document understanding — the world's smallest document-specialist VLM

maestro

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

clipcap

Using pretrained encoder and language models to generate captions from multimedia inputs.

aoa-pytorch

A Pytorch implementation of Attention on Attention module (both self and guided variants), for Visual Question Answering

easy-vqa

The official package for the easy-VQA dataset.

multimodal-maestro

Visual Prompting for Large Multimodal Models (LMMs)

setofmark

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL