HackerTrans
热门最新趋势评论往期问答秀出招聘

rmst

no profile record

提交

[untitled]

1 分·作者 rmst·上个月·0 评论

[untitled]

1 分·作者 rmst·2个月前·0 评论

Wonky Software Supply Chains

simonramstedt.com
1 分·作者 rmst·2个月前·0 评论

Show HN: Transformer Math Explorer

simonramstedt.com
5 分·作者 rmst·2个月前·1 评论

NPM Slop and Wonky Software Supply Chains

simonramstedt.com
2 分·作者 rmst·3个月前·0 评论

评论

rmst
·2个月前·讨论
I made this interactive reference for transformer models, showing everything down to elementary math. I intentionally avoided matrix multiplication and used explicit sums and indices instead. Covers models from GPT-2 to Qwen 3.6, with MLA, MoE, RoPE, MTP, etc togglable. It's best viewed on desktop or tablet.