all AI news
Adaptive Retrieval with Matryoshka Embeddings
Feb. 15, 2024, 4:19 a.m. |
Simon Willison's Weblog simonwillison.net
Adaptive Retrieval with Matryoshka Embeddings
Nomic Embed v1 only came out two weeks ago, but the same team just released Nomic Embed v1.5 trained using a new technique called Matryoshka Representation.
This means that unlike v1 the v1.5 embeddings are resizable - instead of a fixed 768 dimension embedding vector you can trade size for quality and drop that size all the way down to 64, while still maintaining strong semantically relevant results.
Joshua Lochner build this interactive demo on …
ai embed embedding embeddings llms nomic representation retrieval team trade vector
More from simonwillison.net / Simon Willison's Weblog
Understand errors and warnings better with Gemini
1 day, 3 hours ago |
simonwillison.net
PSF announces a new five year commitment from Fastly
1 day, 11 hours ago |
simonwillison.net
Programming mantras are proverbs
1 day, 13 hours ago |
simonwillison.net
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US