Pruning and Distilling Large Language Models - A Path to Efficient AI

Blogs

Pruning and distillation help make large language models smaller, faster, and more efficient while maintaining strong performance. By systematically removing unimportant components and transferring knowledge from larger models, AI can be more accessible and cost-effective.

15 February 2025

LoRA in a nutshell

Cool Topics

LoRA, a Low-Rank Adaptation method, enables more efficient fine-tuning of large language models like GPT-4 by reducing the number of parameters required for adjustment, addressing training time and GPU memory challenges.

19 May 2024

K Nearest Neighbours Algorithm

Ml Algorithms

This algorithm chooses the nearest neighbour of the data point to be of the same class. This algorithm also uses a majority voting mechanim, in read more...

10 September 2021

Intro to neural Networks with Keras

Hands-On Machine Learning2

Inroduction to Deep learning and ANNs. ANNs ( Artificial neural networks) are at the heart of Deep Learning, They are versatile powerful and scalable making them ideal to tackle a number of machine learning tasks.

03 July 2021

Unsupervised Learning Algorithms

Hands-On Machine Learning2

Article describing about some unsupervised learning algorithms

26 May 2021

Dimensionality Reduction

Hands-On Machine Learning2

Article to get you started on Dimensionality Reduction and PCA

19 May 2021

Ensemble Learning and Random Forests

Hands-On Machine Learning2

Details on Ensemble Learning as well as the Random Forests algorithm

12 May 2021

Decision Trees

Hands-On Machine Learning2

Detailed description on Decision Trees

05 May 2021
< Page 1 of 2 >