Learn how to fine-tune large language models (LLMs) locally using aiDAPTIV technology with both the Pro Suite Graphical User Interface and the Command Line Interface. This repository contains all lesson materials, datasets, code examples, and project files to learn aiDAPTIV.
This hands-on curriculum is designed to teach you how to:
- Fine-tune LLMs on your own hardware or a provided remote AI Training PC (AITPC).
- Optimize GPU VRAM usage with aiDAPTIVCache.
- Use both GUI and CLI workflows for training and inference.
- Apply fine-tuning to real-world datasets such as company handbooks or public figure transcripts.
The course includes about 2 hours of recorded, follow-along video content, but the full experience takes around 12 hours to complete.
Most of that time is spent running fine-tuning jobs, so you don’t need to stay at your computer while training is in progress.
Whether you’re a developer, researcher, or student, you’ll gain practical skills to run on-prem AI cost-efficiently and securely.
To take this course, you’ll need access to an AI Training PC.
👉 Click here to request remote access
(Your request will be reviewed, and credentials will be sent to you once approved.)
💻 Step 2: Alternatively, use your own system
If you already have an aiDAPTIV installed on your own hardware, you can skip the reservation form.
👉 Installation instructions for aiDAPTIV
✅ Once you have either remote or local access, you’re ready to begin the lessons.
| Lesson Number | Topic | Lesson Grouping | Learning Objectives | Linked Lesson |
|---|---|---|---|---|
| 01 | Welcome & Introduction | Introduction | Overview of the aiDAPTIV platform, course structure, and how to get started. | lesson video |
| 02 | Accessing the AI Training PC | Introduction | Learn how to request, connect to, and work with the remote AITPC for course exercises. | lesson video |
| 03 | Fine-Tuning via Pro Suite GUI | GUI Based | Use the aiDAPTIV Pro Suite GUI to fine-tune a custom LLM using the Phison Employee Handbook dataset. | lesson video |
| 04 | Instruction Fine-Tuning | CLI Based | Learn how to fine-tune a model on instruction–response datasets for more structured outputs. | lesson video |
| 05 | Speaking Style Model | CLI Based | Fine-tune an LLM to adapt its output style for different tones, audiences, and communication needs. | lesson video |
| 06 | RAFT Dataset Generation | CLI Based | Generate retrieval-augmented datasets to improve factual grounding and domain specialization. | lesson video |
| 07 | LLM as a Judge | CLI Based | Use LLMs to evaluate and grade outputs from other models with rubrics. | lesson video |
| 08 | Vision Function Calling | CLI Based | Explore how Vision-Language Models (VLMs) can analyze images and trigger structured functions. | lesson video |
We’d love to hear your feedback on the aiDAPTIV Training Course!
Please use our feedback form to share your thoughts, suggestions, or issues:
👉 aiDAPTIV Training Course Feedback Form