TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models

TL;DR

TinyLLaVA Factory is an open-source, modular codebase designed to simplify the development, extension, and training of small-scale large multimodal models, making advanced multimodal research more accessible.

Contribution

It introduces a modular, extensible framework for small-scale LMMs with prebuilt training recipes, enhancing usability and reproducibility.

Findings

Empirical validation shows effective training and customization.

Facilitates research with affordable computational resources.

Supports easy extension with new models and features.

Abstract

We present TinyLLaVA Factory, an open-source modular codebase for small-scale large multimodal models (LMMs) with a focus on simplicity of code implementations, extensibility of new features, and reproducibility of training results. Following the design philosophy of the factory pattern in software engineering, TinyLLaVA Factory modularizes the entire system into interchangeable components, with each component integrating a suite of cutting-edge models and methods, meanwhile leaving room for extensions to more features. In addition to allowing users to customize their own LMMs, TinyLLaVA Factory provides popular training recipes to let users pretrain and finetune their models with less coding effort. Empirical experiments validate the effectiveness of our codebase. The goal of TinyLLaVA Factory is to assist researchers and practitioners in exploring the wide landscape of designing and training small-scale LMMs with affordable computational resources.