Kediska Goynta iyo Lakabka Dhicis ee Habaysan

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay sababta manjyada habaysan ay u soo saarto xawaareyn dhab ah halka manjooyin aan habaysan badanaa aanay samayn?
   • Goynta habaysan waxay meesha ka saartaa baloogyada isku xidhan ee dhab ahaantii yareeya teendhooyinka
   • Goynta aan habaysanayn waxay kordhisaa cabbirka qaabka
   • Goynta habaysan waxay ku daraysaa lakabyo badan
   • Goynta aan habaysanayn waxay ku shaqaysaa CPU-yada oo kaliya
2. Waa maxay 'lakabka daadinta' marka loo eego macnaha guud ee transformers?
   • Yaraynta heerka waxbarashada lakabkiiba
   • Tirtirka dhammaan baloogyada beddelka si loo yareeyo qoto dheeraanta moodeelka
   • Ku darida ka tagista lakab kasta
   • Dib u habaynta lakabyada si aan kala sooc lahayn
3. Calaamadee sida caadiga ah tilmaamaysa in lakabka beddelka si badbaado leh loo ridi karo?
   • Lakabku wuxuu leeyahay xuduudaha ugu badan
   • Lakabku waa kan ugu horreeya ee shabakadda
   • Wax gelinta lakabka iyo soo saarida dawladaha qarsoon aad bay isugu dhow yihiin
   • Lakabku wuxuu isticmaalaa xusuusta ugu badan
4. Waa maxay tillaabada sida caadiga ah u soo kabsata saxnaanta ka dib manjooyin habaysan?
   • Kordhinta cabbirka dufcadda kaliya
   • Dib u tirinta ilaa 16 bits
   • Ku darida madax dareen badan
   • Wareeg gaaban oo hagaajinta ama hagaajinta aqoonta
5. Sidee baa madax dareenka shakhsi ahaaneed inta badan loo kala saaraa manjooyin?
   • Marka ay korodho khasaaraha marka madaxa la daboolo (dareenka)
   • Sida alifbeetada u kala horreeyaan
   • By booska ay kaga jiraan ereyada
   • Sida tirada calaamadihii ay arkeen
6. Waa maxay faa'iidada ugu weyn ee isticmaalka manjooyin habaysan oo ay weheliso nadiifinta?
   • Soo saarista xogta tababarka si toos ah
   • Ka soo saarida qoys ka kooban moodooyin yaryar oo dheereeya hal isbaaro weyn
   • Siraynta miisaanka moodeelka
   • Kordhinta dhererka daaqada macnaha guud
7. Why can a smaller student recover some function of a pruned model during distillation?
   • It restores the deleted weights in place
   • It changes the test labels
   • It is trained to match useful outputs or behavior of the larger teacher
   • Waxay ka saartaa baahida loo qabo xaqiijin
8. If a transformer layer’s input and output have high cosine similarity, what does that suggest under the guide’s pruning heuristic?
   • The layer is guaranteed to be useless for every task
   • The model must add another layer
   • The output has no features
   • The layer changed the representation relatively little and may be a candidate for dropping