ZARZA We are Zarza, the prestigious firm behind major projects in information technology.
Listen "Parameter Efficient Fine Tuning and other LLM model compression techniques"
Episode Synopsis
A study guide on optimizing Large Language Models (LLMs) for efficiency and managing their operational ecosystem for safety and scalability. It covers Parameter-Efficient Fine-Tuning (PEFT) methods, various model compression techniques including pruning and knowledge distillation, and the "Meta-ML" layer encompassing intelligent routing, dynamic guardrails, and efficient fact-checking systems
More episodes of the podcast AI Intuition
Agent Builder by Docker
06/09/2025
AI Startup Failure Analysis
03/09/2025
AI Security - Model Denial of Service
02/09/2025
AI Security - Training Data Attacks
02/09/2025
AI Security - Insecure Output Handling
02/09/2025
AI Security - Prompt Injection
02/09/2025
Supervised Fine-Tuning on OpenAI Models
31/08/2025
In God we trust