Explore advanced techniques for optimizing natural language processing models in this lecture from CMU's Advanced NLP course. Delve into the concepts of distillation, quantization, and pruning, essential methods for improving model efficiency and performance. Learn how these techniques can be applied to reduce model size, increase inference speed, and maintain accuracy in NLP applications. Gain insights from Vijay Viswanathan's presentation, part of Graham Neubig's comprehensive course on cutting-edge NLP topics. Enhance your understanding of model optimization strategies crucial for developing practical and scalable NLP solutions.
Overview
Syllabus
CMU Advanced NLP Fall 2024 (11): Distillation, Quantization, and Pruning
Taught by
Graham Neubig
Related Courses
-
Quantization in Depth
-
Optimizing Neural Networks for Efficient Data Processing
-
Compressing Large Language Models (LLMs) with Python Code - 3 Techniques
-
TensorFlow Model Optimization - Quantization and Pruning
-
Pruning and Sparsity in Machine Learning - Part I (EfficientML.ai Lecture 3)
-
Advanced NLP: Prompting and Complex Reasoning - Lecture 7
