PinnedNikhil VermaStraightforward yet productive tricks to boost deep learning model trainingHi fellow Deep Learning researchers,6 min read·Jan 20, 2023----
PinnedNikhil VermaPyTorch’s Magic with Automatic Mixed PrecisionPytorch library is one of the go-to framework used these days for implementing neural networks or deep learning models. These models have…5 min read·Jan 25, 2023--1--1
Nikhil VermaLong-Context Large Language ModelsLanguage modeling has captured the attention of researchers over the years, leading to numerous iterations and modifications of proposed…·4 min read·Jan 22, 2024----
Nikhil VermaBeyond Basics: A Comprehensive Interview Question Bank for DL, NLP, and Diffusion ModelsGone are the days when a basic understanding of machine learning sufficed for tech interviews. Today, employers seek candidates who can…11 min read·Dec 27, 2023----
Nikhil VermaNavigating the Emotional Turbulence of Flight Delay: A Personal Encounter4 min read·Dec 3, 2023----
Nikhil VermainAI AdvancesThe Symphony of Numbers: Inside the GPU’s Power of 2 ArchitectureIn the heart of the data center, where the pulse of artificial intelligence reverberates, lies a remarkable piece of technology — the…·4 min read·Sep 14, 2023--1--1
Nikhil VermaLong-Range Transformer with Unlimited Length InputPretrained transformers generally have a context window of 512 (e.g. BERT , T5 ) or 1024 tokens (e.g. BART), which are sufficient lengths…·3 min read·Aug 25, 2023----
Nikhil VermaLarge Language Models are just another hypeSince the latter part of the previous year, in the midst of a flurry of remarkable technological advancements, ChatGPT has risen as a…5 min read·Jul 15, 2023----
Nikhil VermaRestrictive Freedom with Open Source LicensingDo you know the concept of a “commons” or a shared resource that is accessible to everyone. In medieval times, villages would have a…·5 min read·Apr 15, 2023----