PinnedDev Shah·Nov 29, 2023a picture is worth a 1000 words; breaking down Vision Transformersbreaking down vision transformers with code implementation.A response icon1A response icon1
PinnedDev Shah·Jan 31, 2024build GPT with me! implementing GPT from scratch step-by-stepA step by step guide on implementing GPT from scratch in Python.A response icon2A response icon2
PinnedInAI MindbyDev Shah·Aug 1, 2023why has GPT-4’s accuracy been declining so much!?Understanding the Perplexing Decline of GPT-4’s Accuracy!
Dev Shah·Jun 28VeriCache: Making Lossy KV Compression ExactLong-context inference has made the KV cache one of the main bottlenecks in serving large language models.
Dev Shah·Jul 21, 2024build a multiscale CNN with me! step-by-step guide to implement a multiscale CNN!Implementing a multiscale CNN & understanding the theory / motivation behind building a multiscale CNN.
Dev Shah·Jun 18, 2024build a GAN with me! step-by-step guide on understanding a GAN from scratch!This article goes over what GANs are, how they work, how to implement them from scratch in python & using them on a sample dataset!A response icon2A response icon2
Dev Shah·May 26, 2024build an autoencoder with me!An in-depth breakdown of what an autoencoder is, the math / theory behind them, using them for mnist dataset, and the types of…
Dev Shah·Oct 8, 2023reducing sycophancy in LLMs with synthetic dataHow we can use synthetic data to reduce sycophancy in Large Language Models
Dev Shah·Aug 26, 2023reconstructing music from brain waves!? meet Brain2MusicThis article delves into reconstructing music from brain activity scans with MusicLM!
Dev Shah·Aug 20, 2023Saying bye to segmentation models!? Understanding Universal SegmentationThe main idea of this paper is to leverage a diverse collection of segmentation datasets to co-train a single model for segmentation tasks.