Ikibazo gihuza ibibazo · Hagati Urwego

Ikibazo cyihuse

Ongera usubiremo ibintu byoroshye kumurongo winjiza, imiterere-yahagaritswe, hamwe nubunini-bushingiye kubisubizo byatangajwe kugirango bihute.

Inzira zijyanye no kuyoboraKuringaniza byihuse
Ikibazo 1 Bya 8

Niki 'yoroshye yihuta' mugukurikirana vuba?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Niki 'yoroshye yihuta' mugukurikirana vuba?
    • Wize guhora ushiramo ibice bidakenera ikarita kumagambo nyayo
    • Inyigisho zanditse mu kinyabupfura
    • Kopi ntoya ya kopi yicyitegererezo
    • Gushiraho ibicuruzwa byahagaritswe
  2. Ni hehe guhita byongeweho byongeramo amahugurwa?
    • Kuri buri transformateur
    • Gusa kumurongo winjiza
    • Gusa ku bisohoka
    • Imbere muri reta nziza
  3. Ni izihe ngaruka zitangaje impapuro z'umwimerere zagaragaje ku gipimo cy'icyitegererezo?
    • Kuringaniza byihuse bigenda byiyongera uko moderi ikura
    • Umunzani nta ngaruka ufite muburyo bwihuse
    • Nka moderi ikura nini, guhita utegura uburyo bwiza bwo guhuza neza
    • Moderi nini ntishobora kongera guhita ikurikiranwa
  4. Ninde watangije guhita?
    • DeepMind muri 2016
    • Anthropic muri 2023
    • Microsoft muri 2019
    • Abashakashatsi kuri Google (Lester, Al-Rfou, Constant) mu 2021
  5. Nigute guhita ushyira mubikorwa gukora imirimo myinshi uhereye kumurongo umwe?
    • Buri gikorwa gikoresha akantu koroheje koroheje mugihe icyitegererezo kiguma gikonje
    • Isubiramo icyitegererezo cyose kuri buri cyifuzo
    • Isiba imirimo idakoreshwa muburemere
    • Irasaba GPU itandukanye kuri buri gikorwa
  6. How does Lester and colleagues’ paper describe prompt tuning in relation to prefix tuning?
    • As a replacement for frozen language models
    • As a simpler related method that the paper compares with prefix tuning
    • As a tokenizer with no trainable parameters
    • As a method that updates every model weight
  7. Which model family did Lester and colleagues use to study prompt tuning across scales?
    • Umuhengeri
    • AlphaFold2
    • T5
    • Ishyamba ryo kwigunga
  8. How are soft prompts optimized in prompt tuning?
    • By changing all model weights for each task
    • By replacing embeddings with hard-coded words only
    • By training a new tokenizer for every example
    • By backpropagation through a frozen language model to update the prompt vectors