Test legat de ghid · Mediu Nivel

Test de antrenament pentru predicții cu mai multe jetoane

Review multi-token losses and shared-trunk heads, with DeepSeek-V3’s distinct sequential design, optional inference heads, and target offsets.

Căi de ghidare aferenteAntrenament de predicție cu jetoane multiple
Întrebare 1 de 8

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

Previzualizează fiecare întrebare8 întrebări

Răspunsurile și explicațiile apar pe măsură ce susțineți testul.

  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. Care model a folosit în special un obiectiv de predicție multi-token în preinstruire?
    • Word2Vec original
    • Un clasificator de imagini convoluționale
    • Un model n-gram
    • 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. Ce se întâmplă cu șefii auxiliari după antrenament dacă nu ai nevoie de accelerații?
    • Trebuie să rămână și să dubleze dimensiunea modelului
    • Acestea pot fi eliminate, astfel încât dimensiunea implementării să rămână neschimbată
    • Se transformă în straturi de atenție
    • Ei devin tokenizer
  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