Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.

7b

41.9K 13 months ago

Readme

MedLlama2 by Siraj Raval is a Llama 2-based model trained with MedQA dataset to be able to provide medical answers to questions. It is not intended to replace a medical professional, but to provide a starting point for further research.

CLI

Open the terminal and run ollama run medllama2

API

Example:

curl -X POST http://localhost:11434/api/generate -d '{
  "model": "medllama2",
  "prompt":"A 35-year-old woman presents with a persistent dry cough, shortness of breath, and fatigue. She is initially suspected of having asthma, but her spirometry results do not improve with bronchodilators. What could be the diagnosis?"
 }'

Memory requirements

  • 7b models generally require at least 8GB of RAM

Reference

llSourcell