---
license: mit
pipeline_tag: text-generation
tags:
 - ONNX
 - DML
 - ONNXRuntime
 - phi3
 - nlp
 - conversational
 - custom_code
inference: false
language:
- en
---
# EmbeddedLLM/Phi-3-mini-4k-instruct-062024 ONNX

## Model Summary

This model is an ONNX-optimized version of [microsoft/Phi-3-mini-4k-instruct (June 2024)](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct), designed to provide accelerated inference on a variety of hardware using ONNX Runtime(CPU and DirectML).
DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning, providing GPU acceleration for a wide range of supported hardware and drivers, including AMD, Intel, NVIDIA, and Qualcomm GPUs.

## ONNX Models

Here are some of the optimized configurations we have added:
- **ONNX model for int4 DirectML:** ONNX model for AMD, Intel, and NVIDIA GPUs on Windows, quantized to int4 using AWQ.

## Usage

### Installation and Setup

To use the EmbeddedLLM/Phi-3-mini-4k-instruct-062024 ONNX model on Windows with DirectML, follow these steps:

1. **Create and activate a Conda environment:**
```sh
conda create -n onnx python=3.10
conda activate onnx
```

2. **Install Git LFS:**
```sh
winget install -e --id GitHub.GitLFS
```

3. **Install Hugging Face CLI:**
```sh
pip install huggingface-hub[cli]
```

4. **Download the model:**
```sh
huggingface-cli download EmbeddedLLM/Phi-3-mini-4k-instruct-062024-onnx --include="onnx/directml/Phi-3-mini-4k-instruct-062024-int4/*" --local-dir .\Phi-3-mini-4k-instruct-062024-int4
```

5. **Install necessary Python packages:**
```sh
pip install numpy==1.26.4
pip install onnxruntime-directml
pip install --pre onnxruntime-genai-directml==0.3.0
```

6. **Install Visual Studio 2015 runtime:**
```sh
conda install conda-forge::vs2015_runtime
```

7. **Download the example script:**
```sh
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/phi3-qa.py" -OutFile "phi3-qa.py"
```

8. **Run the example script:**
```sh
python phi3-qa.py -m .\Phi-3-mini-4k-instruct-062024-int4
```

### Hardware Requirements

**Minimum Configuration:**
- **Windows:** DirectX 12-capable GPU (AMD/Nvidia) 
- **CPU:** x86_64 / ARM64
**Tested Configurations:**
- **GPU:** AMD Ryzen 8000 Series iGPU (DirectML)
- **CPU:** AMD Ryzen CPU
  
## Model Description
- **Developed by:** Microsoft
- **Model type:** ONNX
- **Language(s) (NLP):** Python, C, C++
- **License:** Apache License Version 2.0
- **Model Description:** This model is a conversion of the Phi-3-mini-4k-instruct-062024 for ONNX Runtime inference, optimized for DirectML.

## Performance Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->
### DirectML
We measured the performance of DirectML on AMD Ryzen 9 7940HS /w Radeon 78

| Prompt Length | Generation Length | Average Throughput (tps) |
|---------------------------|-------------------|-----------------------------|
| 128 | 128  | 53.46686 |
| 128 | 256  | 53.11233 |
| 128 | 512 | 57.45816 |
| 128 | 1024 | 33.44713 |
| 256 | 128  | 76.50182 |
| 256 | 256  | 66.68873 |
| 256 | 512 | 70.83862 |
| 256 | 1024 | 34.64715 |
| 512 | 128  | 85.10079 |
| 512 | 256  | 68.64049 |
| 512 | 512 | - |
| 512 | 1024 | -  |
| 1024 | 128  | - |
| 1024 | 256  | - |
| 1024 | 512 | - |
| 1024 | 1024 | -  |