Tembiricha uye Sampling Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. Ko kukwidza tembiricha kunoitei kune zvinobuda zvemodhi?
   • Inoita kuti iwedzere deterministic uye inodzokorora
   • Anoshandura zvachose zviyero zvemuenzaniso
   • Inodzima basa reSoftmax
   • Inoita kuti ive yakasarudzika uye yakasiyana-siyana, ine mukana wakawanda wematokeni asina kujairika
2. Usati waita sampling, modhi yakasvibira tokeni zvibodzwa (logits) inoshandurwa kuita zvingangoitika ne:
   • Iyo yepamusoro-k sefa
   • The softmax basa
   • Kudzokera kumashure
   • The tokenizer
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. Mechanically, tembiricha inomboitei kumarogi?
   • Inogovanisa yega yega neT pamberi peSoftmax
   • Inowedzera nhamba isina kurongeka kune yega yega
   • Inodzima zvinyorwa zvakaderera
   • Inowanza zvingangoitika zvekupedzisira naT
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?
   • Vatatu
   • Twelve
   • Vatanhatu
   • Zero
8. For probabilities 0.55, 0.30, 0.10, and 0.05, how many leading tokens does top-p 0.80 keep?
   • Imwe
   • Vatatu
   • Vaviri
   • Zvina