Transformers Without Normalization(jiachenzhu.github.io)247 points by hellollm 1 year ago | 30 comments
The Annotated Kolmogorov-Arnold Network (Kan)(alexzhang13.github.io)27 points by jxmorris12 1 year ago | 1 comments
SentenceTransformers: Python framework for sentence, text and image embeddings(sbert.net)162 points by tosh 2 years ago | 48 comments
No one should use the AT&T syntax (2021)(outerproduct.net)76 points by Tomte 2 years ago | 63 comments