Show HN: Transformer Math Explorer

Interactive reference for transformer models, presented via dataflow graphs, drillable down to elementary mathematical operations. Covers models from GPT-2 to Qwen 3.6, with MLA, MoE, RoPE, MTP, hybrid attention, and other variants toggleable in place.
5 points by rmst 166 days ago simonramstedt.com 1 comments
Summary not yet generated for this article.

Comments (1 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open