Quiz collegato alla guida · Medio Livello

Quiz di formazione sulla previsione multi-token

Esamina le perdite multi-token e le teste del trunk condiviso, con il design sequenziale distinto di DeepSeek-V3, teste di inferenza opzionali e offset target.

Domanda 1 di 8

In the cited Meta study, what architecture predicts several future tokens from a training position?

Anteprima di ogni domanda8 domande

Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.

  1. In the cited Meta study, what architecture predicts several future tokens from a training position?
    • A mandatory separate complete language model for every word
    • Independent output heads above a shared transformer trunk
    • One head that can target only the preceding token
    • A larger vocabulary with no additional prediction targets
  2. Quale modello ha utilizzato in particolare un obiettivo di previsione multi-token nel pre-addestramento?
    • L'originale Word2Vec
    • Un classificatore di immagini convoluzionale
    • Un modello di n grammi
    • DeepSeek-V3
  3. What additional supervision does multi-token training supply at a prefix position?
    • Loss terms for multiple future-token targets
    • Only a larger batch size with the same single target
    • A mandatory image-reconstruction target
    • No prediction loss at any position
  4. How are auxiliary predictions used in the Meta paper’s self-speculative inference experiment?
    • They are accepted unconditionally without verification
    • They automatically retrain the model on every prompt
    • They propose tokens that are then checked by the decoding procedure
    • They encrypt every generated token
  5. Cosa succede alle teste ausiliarie dopo l'allenamento se non servono accelerazioni?
    • Devono rimanere e raddoppiare le dimensioni del modello
    • Possono essere scartati in modo che le dimensioni della distribuzione rimangano invariate
    • Si trasformano in strati di attenzione
    • Diventano il tokenizzatore
  6. Which evaluated task family showed notable gains in the Meta multi-token study?
    • Code generation benchmarks
    • A guarantee of perfect code compilation in every language
    • Only alphabetizing raw filenames
    • A required quantum-sensor prediction task
  7. In a four-head offset design predicting from prefix position t, which token is the fourth head’s target?
    • The token at t−4
    • The token at t+1 for every head
    • Only the token at t itself
    • The token at t+4
  8. What distinguishes DeepSeek-V3’s stated MTP architecture from the cited independent parallel-head implementation?
    • It predicts only tokens before the prefix
    • It requires every target to be an image pixel
    • Sequential auxiliary modules that preserve a causal chain across prediction depths
    • It removes the language-model output vocabulary