Cohere launches open weights AI model Aya 23 with support for nearly two dozen languages

Canadian AI startup Cohere's non-profit research arm, Cohere for AI (C4AI), has announced the release of Aya 23, a new family of multilingual language models. The models, available in 8B and 35B parameter variants, are part of C4AI’s Aya initiative that aims to deliver strong multilingual capabilities. Aya 23, which serves 23 languages, builds on the original model Aya 101 and outperforms other open models like Google’s Gemma and Mistral’s various open source models.

C4AI has released the open weights of both the 8B and 35B models on Hugging Face under the Creative Commons attribution-noncommercial 4.0 international public license. This allows third-party researchers to fine-tune the model to fit their individual needs. However, the release falls short of a full open source release as the training data and underlying architecture have not been released. Users can try out the new models on the Cohere Playground for free.

Key takeaways

Cohere for AI announced the open weights release of Aya 23, a new family of multilingual language models that serves 23 languages and outperforms other open models like Google’s Gemma and Mistral’s various open source models.
The Aya 23 model builds on the original Aya 101 model and is part of C4AI’s Aya initiative that aims to deliver strong multilingual capabilities.
The Aya 23 model improves on discriminative tasks by up to 14%, generative tasks by up to 20%, and multilingual MMLU by up to 41.6% compared to Aya 101.
The open weights for both the 8B and 35B models have been released on Hugging Face under the Creative Commons attribution-noncommercial 4.0 international public license, and users can try out the new models on the Cohere Playground for free.

Cohere launches open weights AI model Aya 23 with support for nearly two dozen languages

Key takeaways

Discussion (0)