.@JinaAI_ just released its binary embeddings, which are 96.875% smaller and faster. For ๐ซ๐ช๐ฏ๐ข-๐ฆ๐ฎ๐ฃ๐ฆ๐ฅ๐ฅ๐ช๐ฏ๐จ๐ด-๐ท2-๐ฃ๐ข๐ด๐ฆ-๐ฅ๐ฆ, binary quantization reduces retrieval accuracy from 44.39% to 42.65%, a loss of only 4%. You might not need all those 32-bits:… https://t.co/SvirgvjQtb https://t.co/9UHc16kkt4
— Qdrant (@qdrant_engine) May 16, 2024
from Twitter https://twitter.com/qdrant_engine
May 16, 2024 at 04:15PM
via IFTTT
No comments:
Post a Comment