https://amey-thakur.github.io/tags/transformers/Recent content in Transformers on AmeyArcHugo -- 0.152.2en-usMon, 16 Mar 2026 15:05:09 -0400https://amey-thakur.github.io/posts/2026-03-16-attention-is-all-you-need/Mon, 16 Mar 2026 15:05:09 -0400https://amey-thakur.github.io/posts/2026-03-16-attention-is-all-you-need/<p><img alt="Cover graphic titled Attention Is All You Need — Understanding the Mathematics of the Transformer. It shows the scaled dot-product attention equation with labeled Query, Key, and Value blocks, plus references to self-attention, multi-head attention, and positional encoding." loading="lazy" src="https://amey-thakur.github.io/posts/2026-03-16-attention-is-all-you-need/attention-fig-1.png"></p> <p><small><em>A visual cover introducing the mathematical foundations of the Transformer architecture from the paper Attention Is All You Need. The graphic highlights the core scaled dot-product attention equation alongside the key components of the architecture: self-attention, multi-head attention, and positional encoding.</em></small></p>