Quiz buy boole model

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

1. Lan mooy njëkka boole model merging?
   • Diisaay yi (parametre yi) ci xeetu model yu bari
   • Done yiñ tàggat ci xeetu model yu bari
   • Xalaatal génnug model yu bari ci diiru inference
   • Gaawaayu hardware bi ñuy jëfandikoo ngir tàggat yaram
2. 'Vecteur de task' mooy:
   • Limu liggéey yi benn model mëna def
   • Seen wuutu ci digganté diisaayu model buñ defar bu baax ak diisaayu modelu base bi
   • Vecteur buy dugal ay token ngir benn liggéey
   • Degrade biñu xayma ci benn jéego tàggat yaram
3. In the described weight-space merging methods, what can be avoided?
   • Evaluation of the merged checkpoint
   • Compatibility requirements between model weights
   • Additional gradient training and access to the original training data
   • Testing the result on intended tasks
4. How do TIES-Merging and DARE differ in addressing parameter interference?
   • Both use the same sign-voting method and differ only in scale
   • DARE uses prompt engineering while TIES retrains on joint data
   • Both average model outputs instead of changing weights
   • They use different techniques: TIES resolves sign conflicts, while DARE drops and rescales task-vector entries
5. Li gëna am solo ngir ñu mëna boole ñaari xeetu liggéey mooy:
   • Séddoo benn architecture te dañuy joge ci benn xeetu base
   • Taggat nañu leen ci ay done yu nuróo
   • Am limu jéego yi nga wara tàggat
   • Jëfandikool benn dayo vokabileer tokenizer bi kese
6. In task arithmetic, what do coefficients control when combining task vectors?
   • Which tokenizer each checkpoint must use
   • How strongly each parameter-change vector contributes to the merged checkpoint
   • How many training examples are generated
   • Whether an evaluation set is required
7. What are the three main stages named by TIES-Merging?
   • Tokenize text, infer emotions, and export audio
   • Quantize weights, shard GPUs, and route network packets
   • Trim small changes, elect a sign direction, then merge aligned parameter updates
   • Train a reward model, collect labels, and run PPO
8. Why should teams evaluate each task after a model merge?
   • Merging guarantees every benchmark improves
   • Evaluation is needed only to calculate the file size
   • A merged model cannot be run without retraining
   • Combining weight updates can create interference or reduce performance on a task