Heerkulka iyo Kediska Muunada

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Muxuu kor u qaadida heerkulka ka qabtaa wax soo saarka moodeelka?
   • Waxay ka dhigtaa mid go'aan qaadasho badan oo soo noqnoqda
   • Si joogto ah u beddela miisaanka moodeelka
   • Wuxuu joojiyaa shaqada softmax
   • Wuxuu ka dhigayaa mid aan kala sooc lahayn oo kala duwan, oo leh fursad badan oo calaamado aan caadi ahayn
2. Muunalada ka hor, buundooyinka calaamada cayriin ee moodeelka (Logits) waxa loo rogaa ixtimaalka iyadoo:
   • Filterka sare-k
   • Shaqada softmax
   • Dib u faafinta
   • Calaamadeeyaha
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. Makaan ahaan, muxuu heerkulku runtii ku sameeyaa saadka?
   • Wuxuu u qaybiyaa logit kasta T ka hor softmax
   • Ku daraa lambar random logiti kasta
   • Tirtiraya saadka ugu hooseeya
   • Ku dhufashada itimaalka ugu dambeeya 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?
   • Saddex
   • Laba iyo toban
   • Lix
   • Eber
8. For probabilities 0.55, 0.30, 0.10, and 0.05, how many leading tokens does top-p 0.80 keep?
   • Mid
   • Saddex
   • Laba
   • Afar