tomaarsen @tomaarsen · 18 Aug 2026
A dense model compresses a whole text into one vector. A multi-vector model keeps one vector per token & scores query against document with MaxSim: for each query token, take its best match in the document, then sum. Nothing has to be averaged away. https://t.co/lXi4HGjAmL
1 968Views
29Likes
0Reposts
1Replies
1Quotes
9Bookmarks
Is that a lot?
3.09×vs this author's median637 views is typical
82Percentile for this authorof 22 recent posts
0.64×vs under 10K median3 068 views is typical
40.88%Reachviews ÷ followers
1.57%Engagement rateof viewers reacted