RecurrentGemma: Moving Past Transformers for Efficient Open Language Models.
Aleksandar BotevSoham DeSamuel L. SmithAnushan FernandoGeorge-Cristian MuraruRuba HarounLeonard BerradaRazvan PascanuPier Giuseppe SessaRobert DadashiLéonard HussenotJohan FerretSertan GirginOlivier BachemAlek AndreevKathleen KenealyThomas MesnardCassidy HardinSurya BhupatirajuShreya PathakLaurent SifreMorgane RivièreMihir Sanjay KaleJuliette LovePouya TaftiArmand JoulinNoah FiedelEvan SenterYutian ChenSrivatsan SrinivasanGuillaume DesjardinsDavid BuddenArnaud DoucetSharad VikramAdam PaszkeTrevor GaleSebastian BorgeaudCharlie ChenAndy BrockAntonia PatersonJenny BrennanMeg RisdalRaj GundluruNesh DevanathanPaul MooneyNilay ChauhanPhil CullitonLuiz GUStavo MartinsElisa BandyDavid HuntspergerGlenn CameronArthur ZuckerTris WarkentinLudovic PeranMinh GiangZoubin GhahramaniClément FarabetKoray KavukcuogluDemis HassabisRaia HadsellYee Whye TehNando de FrietasPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- speech recognition
- n gram
- statistical language models
- language modelling
- information retrieval
- document retrieval
- retrieval model
- query expansion
- test collection
- vector space model
- word error rate
- language models for information retrieval
- relevance model
- information retrieval systems
- hidden markov models