Quiz di AI & Machine Learning: Temperature, Top-k & Top-p

Sampling settings decide how predictable or creative a model's output is. This quiz checks what temperature does to the probabilities, how top-k and top-p (nucleus) sampling filter tokens, and which settings suit which tasks, with a few small numbers to work out.

Medio 10 domande ~6 minuti Superato con il 80%

Scegli una modalità

Stai giocando come ospite: accedi per salvare XP e serie.

Domanda di esempio

Domanda 1 di 10

What does temperature do mathematically?

Mostra la risposta

B. It divides the logits by the temperature before softmax, sharpening or flattening the probabilities Probabilities are softmax(logits / T). A temperature below 1 makes the distribution peakier, above 1 makes it flatter; the weights and the input stay the same.

Cosa copre questo quiz

  • Temperature as dividing the logits before softmax
  • Low vs high temperature, and temperature near 0
  • Top-k and top-p (nucleus) sampling with renormalization
  • Choosing settings for extraction vs brainstorming
  • Repetition and frequency penalties

Domande frequenti

Serve un account?

No. Chiunque può giocare. Accedi per salvare XP, serie, badge e cronologia.

Posso rifarlo?

Sì. Il tuo miglior punteggio resta salvato, e domande e risposte vengono mescolate ogni volta.