Ikibazo gihuza ibibazo · Hagati Urwego

Ubushyuhe no Gutoranya Ikibazo

Gerageza ibipimo by'ubushyuhe bwo gupima, kurarikira umururumba, top-k na nucleus umukandida muyunguruzi, guhagarika imibare, hamwe n'imbibi z'ibisekuruza byavuzwe.

Inzira zijyanye no kuyoboraUbushyuhe no Gutoranya
Ikibazo 1 Bya 8

Niki kuzamura ubushyuhe bikora kumusaruro wicyitegererezo?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Niki kuzamura ubushyuhe bikora kumusaruro wicyitegererezo?
    • Bituma irushaho gushishoza no gusubiramo
    • Guhindura burundu uburemere bwikitegererezo
    • Hagarika imikorere ya softmax
    • Bituma bidashoboka kandi bitandukanye, hamwe amahirwe menshi yikimenyetso kidasanzwe
  2. Mbere yo gutoranya, amanota yikimenyetso cyerekana amanota (logits) ahinduka mubishoboka na:
    • Hejuru-k Akayunguruzo
    • Imikorere ya softmax
    • Gusubira inyuma
    • Ikimenyetso
  3. What determines the candidate set in top-p sampling, compared with top-k?
    • Top-p always keeps exactly ten tokens
    • Both methods always keep every vocabulary token
    • Top-p uses the smallest leading set reaching a cumulative probability threshold; top-k uses a count
    • Top-k uses a cumulative threshold while top-p uses a fixed count
  4. Muburyo bwa tekiniki, mubyukuri ubushyuhe bukora iki kuri logi?
    • Kugabanya buri logit na T mbere ya softmax
    • Ongeraho umubare utemewe kuri buri logit
    • Gusiba inyandiko zo hasi
    • Kugwiza amahirwe yanyuma ya T.
  5. For a structured-data task, what does choosing more predictable token selection fail to establish?
    • That a decoding setting was chosen
    • That the generated content is correct or valid
    • That token scores can be compared
    • That a model can produce an output
  6. How does greedy decoding choose the next token?
    • It literally divides every logit by zero
    • It uniformly samples every vocabulary token
    • It permanently retrains the model
    • It selects a highest-scoring eligible token rather than sampling
  7. Two token logits differ by six before temperature scaling. With positive temperature two, what is their scaled difference?
    • Bitatu
    • Twelve
    • Gatandatu
    • Zeru
  8. For probabilities 0.55, 0.30, 0.10, and 0.05, how many leading tokens does top-p 0.80 keep?
    • Imwe
    • Bitatu
    • Babiri
    • Bane