Ayumaton: A Large Language Model for Ayurveda

Overview

Ayumaton is a large language model fine-tuned on a curated Ayurveda dataset, built on top of the Llama v2 model.
It is designed to provide comprehensive and accurate information on various aspects of Ayurveda, including:

Diagnosing health conditions based on symptoms
Recommending Ayurvedic treatments and remedies
Generating Ayurvedic texts, such as case studies and research papers
Answering questions about Ayurvedic principles and practices

Fine-tuning Details

Base Model: Llama v2
Dataset: Curated Ayurveda dataset [https://huggingface.co/datasets/Macromrit/ayurveda-text-based-qanda]
Fine-tuning Task: Question Answering & Text Generation
Evaluation Metrics: BLEU 1 : 0.116406 ; BLEU 2 : 0.051808

Disclaimer

Ayumaton is a research model and should not be used as a substitute for professional medical advice. Always consult with a qualified Ayurvedic practitioner before making any health-related decisions.

License

Ayumaton is licensed under the Apache 2.0 License.

Contact

For any questions or feedback, please contact [[email protected]]