Re:Show HN: Boomerang, a new embedding model for RAG and sem...
by K0IN on Sunday October 01, 2023 @09:21AM
(#37725695)
> Note that while Boomerang is optimized for low-latency performance, models like GTR-XXL, which weighs in at 4.8 billion parameters, are very challenging to productionize.
So what is the size of your model than,
or did i miss something?
So what is the size of your model than, or did i miss something?