Search papers, labs, and topics across Lattice.
Tiny Aya, a 3.35B parameter multilingual language model, was trained on 70 languages and refined with region-aware post-training. It achieves state-of-the-art translation quality and strong multilingual understanding, demonstrating high-quality target-language generation. The release includes a pretrained model, an instruction-tuned variant, and three region-specialized models, showcasing a scaling path focused on efficiency and balanced performance.
Forget brute-force scaling: Tiny Aya proves a 3B parameter model can achieve state-of-the-art multilingual performance with clever training and region-aware specialization.
Tiny Aya redefines what a small multilingual language model can achieve. Trained on 70 languages and refined through region-aware posttraining, it delivers state-of-the-art in translation quality, strong multilingual understanding, and high-quality target-language generation, all with just 3.35B parameters. The release includes a pretrained foundation model, a globally balanced instruction-tuned variant, and three region-specialized models targeting languages from Africa, South Asia, Europe, Asia-Pacific, and West Asia. This report details the training strategy, data composition, and comprehensive evaluation framework behind Tiny Aya, and presents an alternative scaling path for multilingual AI: one centered on efficiency, balanced performance across languages, and practical deployment.
Google Research
Microsoft Research
Mila