AI Fine Tuning and Data Preparation for Pre-Trained Models

You will develop the skills to gather, clean, and organize data for fine-tuning pre-trained LLMs and Generative AI models. Through a combination of lectures and hands-on labs, you will use Python to fine-tune open-source Transformer models. Gain practical experience with LLM frameworks, learn essential training techniques, and explore advanced topics such as quantization. During the hands-on labs, you will access a GPU-accelerated server for practical experience with industry-standard tools and frameworks.

By the end of this course, participants will be able to:

• Clean, prepare, and curate data for AI fine-tuning
• Establish guidelines and best practices for acquiring raw training data
• Transform large, unstructured datasets into clean, usable training data
• Fine-tune AI models using PyTorch
• Understand core AI architectures, including Transformer models
• Explain tokenization, word embeddings, and their role in model performance
• Install, configure, and use AI frameworks such as Llama 3
• Perform parameter-efficient fine-tuning using LoRA and QLoRA
• Apply model quantization techniques to optimize performance and efficiency
• Deploy fine-tuned models and maximize inference performance

• Project Managers
• Architects
• Developers
• Data Acquisition Specialists

• Python or Equivalent Experience
• Familiarity with Linux