Nikhil Verma – Medium

Nikhil Verma

Pinned

Straightforward yet productive tricks to boost deep learning model training

Hi fellow Deep Learning researchers,

Jan 20, 2023

Straightforward yet productive tricks to boost deep learning model training

Jan 20, 2023

Pinned

PyTorch’s Magic with Automatic Mixed Precision

Pytorch library is one of the go-to framework used these days for implementing neural networks or deep learning models. These models have…

Jan 25, 2023

PyTorch’s Magic with Automatic Mixed Precision

Jan 25, 2023

Scale baby Scale — Test-time scale!

Inference scaling or Test-time scaling is the latest buzzword capturing the interest of everyone working in the high-boiling field of AI…

3d ago

Scale baby Scale — Test-time scale!

3d ago

Long-Context Large Language Models

Language modeling has captured the attention of researchers over the years, leading to numerous iterations and modifications of proposed…

Jan 22, 2024

Long-Context Large Language Models

Jan 22, 2024

Beyond Basics: A Comprehensive Interview Question Bank for DL, NLP, and Diffusion Models

Gone are the days when a basic understanding of machine learning sufficed for tech interviews. Today, employers seek candidates who can…

Dec 27, 2023

Beyond Basics: A Comprehensive Interview Question Bank for DL, NLP, and Diffusion Models

Dec 27, 2023

Navigating the Emotional Turbulence of Flight Delay: A Personal Encounter

Dec 3, 2023

Navigating the Emotional Turbulence of Flight Delay: A Personal Encounter

Dec 3, 2023

Finding attention Sink of LLMs: StreamingLLM

Oct 16, 2023

Finding attention Sink of LLMs: StreamingLLM

Oct 16, 2023

Published in
AI Advances

The Symphony of Numbers: Inside the GPU’s Power of 2 Architecture

In the heart of the data center, where the pulse of artificial intelligence reverberates, lies a remarkable piece of technology — the…

Sep 14, 2023

The Symphony of Numbers: Inside the GPU’s Power of 2 Architecture

Sep 14, 2023

Long-Range Transformer with Unlimited Length Input

Pretrained transformers generally have a context window of 512 (e.g. BERT , T5 ) or 1024 tokens (e.g. BART), which are sufficient lengths…

Aug 25, 2023

Long-Range Transformer with Unlimited Length Input

Aug 25, 2023

Large Language Models are just another hype

Since the latter part of the previous year, in the midst of a flurry of remarkable technological advancements, ChatGPT has risen as a…

Jul 15, 2023

Large Language Models are just another hype

Jul 15, 2023

Nikhil Verma

Nikhil Verma

Knowledge shared is knowledge squared | My Portfolio https://lihkinverma.github.io/portfolio/ | My blogs are living document, updated as I receive comments

Following

Help
Status
About
Careers
Press
Blog
Privacy
Rules
Terms
Text to speech