| To run inference with this model, please follow below steps - | |
| 1. Install Nvidia Graphics driver R565 or higher. | |
| 2. Install python 3.10.11. | |
| 3. Setup GenAI DirectML via | |
| a. Install numpy - pip install numpy==2.1.0 | |
| b. Install GenAI - pip install onnxruntime-genai-directml==0.5.0 | |
| 4. Download inference script - curl https://github.com/microsoft/onnxruntime-genai/blob/rel-0.5.0/examples/python/phi3-qa.py -o phi3-qa.py | |
| 5. Run inference - python phi3-qa.py -m <model-downloaded-path> | |
| a. Enter prompt - "What is GenAI?" |