Welcome to TinyLLaVA_Factory’s Documentation!

We present TinyLLaVA Factory, an open-source modular code repository 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 effort of coding. Empirical experiments validate the effectiveness of our code repository. The goal of TinyLLaVA Factory is assisting researchers and practitioners to explore the wide landscape of designing and training small-scale LMMs with affordable computational resources.

Code: https://github.com/TinyLLaVA/TinyLLaVA_Factory

Documentation: https://tinyllava-factory.readthedocs.io/en/latest/