quiz bu lëkkale ak tegtal · Diggante Niveau

Quiz formatu sérialisasioŋ model

Dafay saytu portabilite serialisasioŋ, kaaraange pickle, fichier yu poids tensor kese, ak xool model yiñ exporte ci runtime yi.

Yooni njiit yu jëm ciFormat serialisasioŋ model
Laaj 1 de 8

Lan moo waral ñuy jàppee formaa pickle bu Python ni risku kaaraange ci model yi?

Xoolaatal laaj bu nekk8 laaj

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

  1. Lan moo waral ñuy jàppee formaa pickle bu Python ni risku kaaraange ci model yi?
    • Soo ko sargee mën na def kode bu nekk buñ samp ci biir fichier bi
    • Dafay kompresse fichier yi lu bari
    • Ci njeexte ayu-bis yi kese lay liggéey
    • Dafay efaase model bi njëkk
  2. Lan mooy njariñu format ONNX?
    • Mooy formaa bi gëna ndaw
    • Dafay may ab model buñu tàggat ci benn kaadar mu dox ci yeneen runtime ak làkk yu bari
    • Mën nañu ko ubbi ci PyTorch
    • Dafay yokk njub ci saasi
  3. Lan moo waral safetensors nekk lu siiw ci séddoo poids model?
    • Dafay doxal kode ci sarse ngir yombal
    • Mooy formaa bi gëna yàgg
    • Dafay denc lenn ludul done tensor ci anam wu wóor, ak chargement bu gaaw buñu mëna karte ci mémoire bi te amul benn code execution
    • Dafay denc model bu jaar yoon
  4. GGUF moo gëna méngoo ak ban jëfandikoo?
    • Dencukaay këyitu xayma
    • Enkripte ay imeel
    • Royuwaayi tàggat yaram ci cloud bi
    • Doxal ay modelu làkk yu yaatu ci anam wu jaar yoon ci kaw aparey bi ci dëkk bi
  5. Lan la formaa weccoo bu melni ONNX di njëkka denc?
    • Graafiku ordinatër buñ yamale ak diisaayu model bi
    • Wideo buy wane ni ñuy tàggatee
    • Done yiñ tàggat kese
    • Kodu cosaanu defarkat bi
  6. When exporting a Keras 3 model for TensorFlow serving, which directory format can model.export produce?
    • GGUF
    • Model buñ denc
    • CSV
    • A pickle file containing the entire Python application
  7. After exporting a model to ONNX for a new runtime, what should the team check?
    • That the ONNX file guarantees identical speed on every device
    • That the export automatically includes the original training data
    • That supported operators run and outputs match the reference model on representative inputs
    • That no preprocessing code is needed
  8. Why can a state-dictionary checkpoint be preferable to loading a whole Python object from an untrusted file?
    • It guarantees the model architecture is embedded
    • It makes every checkpoint safe regardless of loader and version
    • It automatically converts the model to ONNX
    • It can load tensor state without reconstructing arbitrary pickled Python objects, subject to the loader’s security settings