---
license: apache-2.0
language:
  - en
tags:
  - medgemma
  - ayurveda
  - healthcare
  - instruction-tuning
  - lora
  - 4bit
datasets:
  - Macromrit/ayurveda-text-based-qanda
library_name: transformers
pipeline_tag: text-generation
model-index:
  - name: MedGemma Ayurvedic LoRA
    results: []
---

# MedGemma 4B - LoRA Fine-tuned on Ayurveda Q&A

This model is a fine-tuned version of [`google/medgemma-4b-it`](https://huggingface.co/google/medgemma-4b-it) using LoRA (Low-Rank Adaptation) in 4-bit precision, trained on the [`Macromrit/ayurveda-text-based-qanda`](https://huggingface.co/datasets/Macromrit/ayurveda-text-based-qanda) dataset.  
It specializes in answering healthcare and Ayurvedic medical questions in an instruction-following format.

---

## 🧠 Model Details

- **Base model:** `google/medgemma-4b-it`
- **Fine-tuned with:** LoRA + 4-bit quantization
- **Training data:** [Macromrit/ayurveda-text-based-qanda](https://huggingface.co/datasets/Macromrit/ayurveda-text-based-qanda)
- **Task:** Instruction-tuned text generation for Ayurveda Q&A
- **Language:** English
- **License:** Apache 2.0

---