AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda
AyurParam is a domain-specialized, bilingual language model fine-tuned from Param-1-2.9B using an extensive, curated Ayurveda dataset in Sanskrit, Hindi, and English. It was tested on BhashaBench-Ayur and achieved state-of-the-art performance (up to 41.12% accuracy in Hindi). This work demonstrates that domain adaptation significantly improves small models for specialized knowledge tasks like Ayurveda.