LaVy: Vietnamese Multimodal Large Language Model

<PRE_TAG>Large Language Models (LLMs)</POST_TAG> and Multimodal Large language models (MLLMs) have taken the world by storm with impressive abilities in complex reasoning and linguistic comprehension. Meanwhile there are plethora of works related to Vietnamese Large Language Models, the lack of high-quality resources in multimodality limits the progress of Vietnamese MLLMs. In this paper, we pioneer in address this by introducing <PRE_TAG><PRE_TAG>LaVy</POST_TAG></POST_TAG>, a state-of-the-art Vietnamese MLLM, and we also introduce <PRE_TAG><PRE_TAG><PRE_TAG><PRE_TAG><PRE_TAG>LaVy</POST_TAG></POST_TAG>-Bench</POST_TAG></POST_TAG></POST_TAG> benchmark designated for evaluating MLLMs's understanding on <PRE_TAG><PRE_TAG>Vietnamese visual language tasks</POST_TAG></POST_TAG>. Our project is public at https://github.com/baochi0212/<PRE_TAG><PRE_TAG>LaVy</POST_TAG></POST_TAG>