[RCAC Workshop]Finetuning & Compression of LLMs (LoRA, QLoRA, GGUF)

📅 Date: October 30th, 2026 ⏰ Time: 11AM-12PM 💻 Location: Virtual 🏫 Instructor: Mansi Sharma

As large language models grow in size and capability, deploying and customizing them efficiently has become a critical skill for AI practitioners. This workshop demystifies parameter-efficient finetuning (PEFT) and model compression techniques that make it possible to adapt and run LLMs without massive compute budgets. Participants will explore the theory and intuition behind LoRA and QLoRA, understand how quantization formats like GGUF enable local and edge deployment, and walk through real-world architecture and design tradeoffs.

Who Should Attend

ML/AI engineers and data scientists who want to understand model customization beyond prompting Software engineers building AI-powered products who need to reason about deployment cost and tradeoffs Researchers or students exploring efficient training methods for constrained hardware Anyone curious about how open-source LLMs are finetuned and compressed for local or edge use

Prerequisites: Basic familiarity with how neural networks and transformers work.

🔗 Register now: LINK