Bengaluru firm launches micro language model for climate-smart farming
Bengaluru: Imagine a tool that not only predicts the onset of weather anomalies like the current heat wave, but also alerts farmers about what can be done with specific reference to the crops that they have chosen to cultivate.
Thanks to rapid progress in Artificial Intelligence (AI) this may soon be possible. A stepping stone in that direction is Aksara, an open-source micro language model launched by Bengaluru-based agri-tech firm, Cropin Technology.
Aksara promises to enable farmers with the right kind information, hyper-tuned to local conditions and crops, so that they can make climate-smart decisions.
The existing large language model, which served as the base model for Aksara, is fed with more generic data, which are biased towards the Global North, said Krishna Kumar, founder and CEO of Cropin.
“What we have done with Aksara is that we fine-tuned contextual data on nine kinds of crops – paddy, wheat, maize, sorghum, barley, cotton, sugarcane, soybean and millets – with particular reference to countries in the Indian subcontinent,” added Kumar.
