Fine-Tuning LLMs Using LoRA and QLoRA

An understanding of the fundamentals of fine-tuning LLMs in machine learning and the various fine-tuning techniques

Familiarity with LLM quantization and its role in reducing model size for efficient deployment, including techniques like int8 quantization and bitsandbytes quantization

Hands-on experience implementing quantization techniques to optimize models

An understanding of Low-Rank Adaptation (LoRA) and Quantized Low-Rank Adaptation (QLoRA) for parameter-efficient fine-tuning (PEFT)

Hands-on experience fine-tuning the Llama 3 model using custom datasets