T5 ak Quiz buy joxe mbind ci mbind

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Lan mooy xalaat bi gëna fësal T5?
   • Tekki làkku masin rek lay def
   • Dafay defar ay nataal ci biir mbind yi
   • Bépp liggéeyu NLP dañu ko kaadre ni dugal mbind ngir génne mbind
   • Dafay wecci bépp tàggat ak jàng buy dooleel
2. Ban arsitektir transformatër la T5 di jëfandikoo?
   • Enkodeer-dekodeer bu mat
   • Encoder kese, melni BERT
   • Dekodeer kese, melni GPT
   • Amul benn ndànk
3. Ban mébetu tàggat yaram la T5 njëkka jëfandikoo?
   • Xalaatal frase bi ci topp kese
   • Xalaatal njëgi aksioŋ yi
   • Nataal ci peinture
   • Ger span, maske span yu jegewaale ñu wecci leen ay jeton sentinel
4. Ban corpus lañu njëkka tàggat T5?
   • Wikipedia kese
   • Corpus C4 Colossal bu sell
   • ab done bu kodu cosaan
   • Transkripsioŋ audio
5. Ak naka la T5 di màndargaale liggéeyu xaaj bu melni jàngat yëg-yëg?
   • Dafay genne vecteur probabilite kese
   • Dafay delloo ID nimero
   • Dafay defar baat etiketu literal, lu melni 'positif' wala 'négatif'
   • Mënul def xaaj
6. Luy FLAN-T5 buñu ko méngale ak T5 bi njëkk?
   • Benn xeetu nataal bu gëna ndaw
   • Descendant buñ méngale ak tegtal buy yamale liggéey yuñu gisul
   • Sistem buy xàmmee kàddu
   • Jumtukaayu base de done bu amul benn lëkkaloo
7. When T5 generates a summary, what does decoder cross-attention let it consult?
   • The encoder's representations of the input article
   • Only previously generated summary tokens
   • Only the unprocessed task label
   • The training optimizer's stored gradients
8. In a closed-book T5 question-answering setup, where does the answer's factual information come from at inference?
   • A document retrieval step required for every question
   • A newly supplied answer passage required in the prompt
   • A live database lookup built into span corruption
   • Knowledge encoded in the model's learned parameters