AyurGPT: Fine-Tuning a Medical LLM for Multilingual Ayurveda Consultations
This talk shares key findings, learnings, and a demo from developing AyurGPT, a large language model specialized for medicine consultations on Ayurveda, the traditional Hindu system of medicine.
This LLM is optimized to pursue these goals:
- Enhance understanding of Ayurvedic terminology
- Improve diagnostic approach comprehension
- Better treatment recommendation capabilities
AyurGPT is a fine-tuned version of BioGPT-Large-PubMedQA, built using the PubMedQA dataset for synthetic data generation, and a mix of real and synthetic Ayurveda-specific consultations.
The model supports English, Kannada, Tamil, and Malayalam, and we’ll share metrics on its performance in the following tasks: Medical question answering Generation of culturally appropriate responses in multiple languages.
Anand Padia
Global Head & AVP, GenAI and Program Management at Trigent Software, Inc.
Andy, recognized as a LinkedIn Top Voice, brings over two decades of expertise in product and project management with a rich focus on hyperautomation. As the Global Head & AVP for GenAI and Program Management at Trigent Software Inc., Andy leads innovative AI and hyperautomation initiatives. His extensive experience spans product development, Agile methodologies, and pioneering research in 1-bit models. Andy’s dedication to advancing AI technologies ensures impactful contributions and thought leadership in the field.
