Cohere's Tiny Aya Base 32K is a multilingual starting point for further training. The model card describes a 3.35-billion-parameter model trained across more than 70 languages, with a 32K-tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → allowance shared between the prompt and generated output. It has not been trained to follow instructions or align with conversational preferences, so the supplied usage follows text-completion patterns. The longer context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → supports research and adaptation involving longer passages, while a conversational assistant would require additional post-training. The release is offered under a noncommercial license.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
