"The model, launched by the company's research arm Cohere Labs, supports South Asian languages such as Bengali, Hindi, Punjabi, Urdu, Gujarati, Tamil, Telugu, and Marathi. The base model contains 3.35 billion parameters - a measure of its size and complexity. Cohere has also launched TinyAya-Global, a version fine-tuned to better follow user commands, for apps that require broad language support."
"Regional variants round out the family: TinyAya-Earth for African languages; TinyAya-Fire for South Asian languages; and TinyAya-Water for Asia Pacific, West Asia, and Europe. This approach allows each model to develop stronger linguistic grounding and cultural nuance, creating systems that feel more natural and reliable for the communities they are meant to serve. At the same time, all Tiny Aya models retain broad multilingual coverage, making them flexible starting points for further adaptation and research,"
Cohere launched Tiny Aya, an open-weight family of multilingual models that support over 70 languages and can run on everyday devices without internet access. The base model has 3.35 billion parameters. TinyAya-Global is a fine-tuned variant optimized to follow user commands. Regional models include TinyAya-Earth for African languages, TinyAya-Fire for South Asian languages, and TinyAya-Water for Asia Pacific, West Asia, and Europe. Training used a single cluster of 64 Nvidia H100 GPUs with relatively modest compute. The software is optimized for on-device usage, reducing compute needs and enabling offline translation and native-language applications for diverse regions.
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]