Overview
The Edge AI Tuning Kit enables you to build and fine-tune AI models on Intel platforms using a no-code interface. It streamlines model and dataset management, fine-tuning, and evaluation for efficient deployment.
Benefits
Unlocking AI potential at the edge—without the complexity.
Accuracy
Prevents AI from giving wrong answers or context, boosting reliability in real-world applications.
Cost Efficiency
Run models directly on edge devices to avoid expensive cloud service bills—ideal for budget-conscious deployments.
Data Privacy
Keep sensitive data on premises. No need to send it to the cloud, ensuring compliance and security.
Use Case Enhancement
Easily integrate AI into your existing solutions—whether it’s for automation, analytics, or customer interaction.
Seamless Dataset Integration
Feed your own data into the models to make them smarter and more relevant to your business.
How It Works
Streamlined model tuning for real-world edge performance. Follow the steps shown here to get started.
- View or Download Edge AI Tuning Kit source files from public repository link on Github.
- To pull Edge AI Tuning Kit source files, simply use git clone command on a command line console as shown here.
git clone https://github.com/open-edge-platform/edge-ai-tuning-kit
Click the image for the full view.
Edge AI Tuning Kit relies on three components.
- Mistralai/Mistral-7B-Instruct-v0.3 LLM model.
- Docker*
- System Bring Up Scripts Edge Developer Kit Reference Scripts.
Please follow the instructions found here to prepare your system before continuing.
To initiate installation, add the current user to Docker Group and begin installation with the commands shown below.
sudo usermod -aG docker $USER
git clone https://github.com/open-edge-platform/edge-ai-tuning-kit
cd edge ai-tuning-kit/
./setup.sh -bRun the application in the terminal and launch a web browser to http://localhost and follow the rest of the steps in the next section.
./setup.sh -r
Click the image for the full view.
Get Started
From model to edge, we’ve simplified your AI development journey. Follow the steps below to get started—and feel free to reach out if you need any help along the way.
Download an AI model – Download a pre-trained model that is related to your use-case
Click the image for the full view.
Create a Project – Create a project that is meaningful to your task
Click the image for the full view.
Customize your prompt that meets your use-case
Click the image for the full view.
Upload your dataset
Click the image for the full view.
Fine-tune AI model with the dataset
Click the image for the full view.
Verify AI model performance
Click the image for the full view.
Evaluate
Click the image for the full view.
Deploy Optimized AI Model at the Edge with OpenVINO™
Click the image for the full view.
Try the Edge AI Tuning Kit on the Testbed
The Edge AI Tuning Kit helps you get the most out of your resources. Use our testbed to see how it accurately recommends the right resource allocation and helps prevent over-provisioning.
Try on Testbed
Support
Provides comprehensive support for Edge AI and Intel technologies, delivered by global professional technical experts.
Request for SupportSubscribe To Our Newsletter
Subscribe to the newsletter for the latest updates on materials posted on the Intel Industry Solution Builders program.
By submitting this form, you are confirming you are an adult 18 years or older and you agree to share your personal information with Intel to use for this business request. You also agree to subscribe to stay connected to the latest Intel technologies and industry trends by email and telephone. You may unsubscribe at any time. Intel’s websites and communications are subject to our Privacy Notice and Terms of Use.
By submitting this form, you are confirming you are an adult (18 years or older) and you agree to share your personal information with Intel to use for this business request. You also agree to subscribe to stay connected to the latest Intel technologies and industry trends by email. You may unsubscribe at any time. Intel’s websites and communications are subject to our Privacy Notice and Terms of Use.