LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model

arXiv:2404.01331v1 Announce Type: new
Abstract: We train a suite of multimodal foundation models (MMFM) using the popular LLaVA framework with the recently released Gemma family of large language models (LLMs). Of particular interest is the 2B parameter Gemma model, which provides opportunities to construct capable small-scale MMFMs. In line with findings from other papers in this space, we test the effect of ablating three design features: pretraining the connector, utilizing a more powerful image backbone, and increasing the size of …

abstract arxiv compact construct cs.ai cs.cl family foundation framework gemma language language model language models large language large language models line llava llms multimodal opportunities popular scale small train type