Login / Signup

Mixture of Tokens: Efficient LLMs through Cross-Example Aggregation.

Szymon AntoniakSebastian JaszczurMichal KrutulMaciej PióroJakub KrajewskiJan LudziejewskiTomasz OdrzygózdzMarek Cygan
Published in: CoRR (2023)
Keyphrases
  • mixture model
  • real time
  • neural network
  • search engine
  • computationally expensive
  • data sets
  • databases
  • real world
  • information systems
  • decision making
  • database systems
  • computationally efficient
  • line segments