HackerTrans
トップ新着トレンドコメント過去質問紹介求人

anarmorarm

no profile record

投稿

Show HN: WaveletLM – wavelet-based, attention-free model with O(n log n) scaling

github.com
7 ポイント·投稿者 anarmorarm·3 か月前·1 コメント

コメント

anarmorarm
·3 か月前·議論
Edit: GPT-2, not GPT-2 Medium. The 2nd paragraph should read:

"With 23.8 PPL on WikiText-103, WaveletLM beats both GPT-2, which was trained on 80× more data, and Transformer-XL Standard, which..."
anarmorarm
·4 年前·議論
This deserves to be on the front page. Fantastic read.