---
license: apache-2.0
pipeline_tag: text-generation
tags:
 - ONNX
 - DML
 - DirectML
 - ONNXRuntime
 - mistral
 - conversational
 - custom_code
inference: false
---

# Mistral-7B-Instruct-v0.3 ONNX

## Model Summary

The [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) is an optimized version of the Mistral-7B model, fine-tuned for instruction-based tasks. This model is available in ONNX format to accelerate inference using ONNX Runtime, specifically optimized for 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.

## Model Description

- **Developed by:** Mistral AI
- **Model type:** ONNX
- **Language(s) (NLP):** Python, C, C++
- **License:** Apache License Version 2.0
- **Model Description:** This model is a conversion of the Mistral-7B-Instruct-v0.3 for ONNX Runtime inference, optimized for CPU and DirectML.

## Usage

### Installation and Setup

To use the Mistral-7B-Instruct-v0.3 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/mistral-7b-instruct-v0.3-int4-onnx-directml --include directml/* --local-dir .\mistral-7b-instruct-v0.3
```

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

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 .\mistral-7b-instruct-v0.3
```

### 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

## Optimized Configurations

The following optimized configurations are available:

1. **ONNX model for int4 DML:** Optimized for AMD, Intel, and NVIDIA GPUs on Windows, quantized to int4.
2. **ONNX model for int4 CPU:** Optimized for CPU, using int4 quantization.