Introducing Aya

The Aya Collection stands as the most extensive assembly of multilingual instruction fine-tuning datasets to date, featuring 513 million prompts and completions across 114 languages. We fully open-source the collection, which includes rare, human-curated annotations from fluent speakers worldwide.

The Aya Model is a massively multilingual language model capable of following instructions in 101 languages. Developed using a diverse mix of instructions from the Aya dataset and collection among others, it achieves state-of-the-art performance across numerous multilingual benchmarks.

Aya 23 was an earlier iteration of our Aya Expanse models. Our technical report shares evaluation results on multiple multilingual NLP benchmarks, and generation quality assessments.

We introduce the Aya Expanse model family, a new generation of 8B and 32B parameter multilingual language models, aiming to address the critical challenge of developing highly performant multilingual models that match or surpass the capabilities of monolingual models.

To address the challenges of building multimodal language models, we introduce novel techniques spanning both data & modeling, resulting in Aya Vision 8B and 32B models. Our work provides insights into techniques that effectively bend the need for compute while delivering extremely high performance.