Parameter-Efficient Fine-Tuning (PEFT) Techniques for LLMs Training Course

Foundations of Parameter-Efficient Fine-Tuning (PEFT)

• Drivers and constraints associated with full fine-tuning
• Introduction to PEFT: objectives and advantages
• Real-world industrial applications and use cases

LoRA (Low-Rank Adaptation)

• Core concepts and intuitive understanding of LoRA
• Building LoRA implementations with Hugging Face and PyTorch
• Practical session: Fine-tuning a model using LoRA

Adapter Tuning

• Mechanics of adapter modules
• Integration strategies for transformer-based architectures
• Practical session: Applying Adapter Tuning to transformer models

Prefix Tuning

• Utilising soft prompts for effective fine-tuning
• Comparative strengths and limitations relative to LoRA and adapters
• Practical session: Executing Prefix Tuning on LLM tasks

Assessment and Comparison of PEFT Methods

• Key metrics for judging performance and efficiency
• Balancing training speed, memory consumption, and accuracy
• Conducting benchmark experiments and interpreting outcomes

Deployment of Fine-Tuned Models

• Processes for saving and loading fine-tuned models
• Strategic considerations for deploying PEFT-based solutions
• Seamless integration into existing applications and pipelines

Best Practices and Advanced Extensions

• Synergising PEFT with quantization and distillation techniques
• Application in low-resource and multilingual environments
• Exploring future trajectories and current research frontiers