# Efficient Lightweight

Eagle2 is a high-performance vision-language model family introduced by NVIDIA, focusing on enhancing the performance of open-source vision-language models through data strategies and training approaches. Eagle2-2B is the lightweight model in this series, achieving outstanding efficiency and speed while maintaining robust performance.

Text summarization model fine-tuned on google/t5-efficient-tiny, trained on the billsum dataset

An information retrieval model optimized based on the TinyBERT architecture, specifically trained for the MS Marco passage ranking task