Ikibazo gihuza ibibazo · Hagati Urwego

Ikibazo

Ongera usuzume indangagaciro-yuzuye, uburemere bwiza bwo kwishyurwa, kuzenguruka, GPTQ na AWQ kalibrasi, intungamubiri, uburemere-bumenya uburemere, kode ya affine, na QAT.

Inzira zijyanye no kuyoboraUmubare
Ikibazo 1 Bya 8

Mu buryo bwo gukora ubugenzuzi bwibanda ku bintu, ni ikihe gikorwa cy'ubugenzuzi cyahindutse?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Mu buryo bwo gukora ubugenzuzi bwibanda ku bintu, ni ikihe gikorwa cy'ubugenzuzi cyahindutse?
    • The mandatory number of network layers
    • The identity of every original training document
    • The numerical levels or precision used for selected weights
    • Only the displayed model title
  2. Kwibagirwa metadata n'ibindi by'ububiko bw'akazi, ni ikihe gice cy'ibipimo by'ibiro by'ubugenzuzi byibanze rihagaze igihe uhuza ibiro by'ubugenzuzi bimwe na bimwe kuva kuri 16-bit kugeza kuri 4-bit?
    • The same amount
    • Twice as much
    • One-hundredth in every case
    • One-quarter
  3. Ni izihe ngaruka nyamukuru zo kugereranya ubukana?
    • Ikosa ryo kuzenguruka rishobora kugabanya urugero rwukuri
    • Icyitegererezo ntigishobora gukururwa
    • Isiba burundu amakuru yamahugurwa
    • Burigihe bituma icyitegererezo kigenda gahoro
  4. Kuki uburyo bwa GPTQ na AWQ bwerekana amakuru y'ubugenzuzi?
    • To guarantee identical performance on every future input
    • To guide their respective weight-quantization choices and error management
    • To translate the vocabulary into another language
    • To add a required number of new transformer layers
  5. Kuki igipimo cy'igihe cyakorwa cyakorwa aho kwemeza gusa ku bitaramo by'ibiro by'ubugenzuzi?
    • A bitwidth label guarantees an identical speedup on every device
    • All quantized values remove the need for computation
    • Every compressed model must be slower by definition
    • Kernels, hardware, and conversion overhead also affect runtime
  6. What does activation-aware mean in the cited AWQ weight-quantization method?
    • Every activation must be stored at the same low bitwidth as every weight
    • The weights are never quantized
    • Activation observations help choose salient weight scaling
    • The method uses only parameter names without input observations
  7. Using the stated reconstruction rule scale times code minus zero point with subtraction inside, what value comes from code six, scale 0.5, and zero point two?
    • Bane
    • Babiri
    • Bitatu
    • Gatandatu
  8. How does quantization-aware training differ in timing from post-training quantization?
    • Training incorporates quantization effects so learned values can adapt
    • It is defined as changing only a fitted model after every training stage ends
    • It forbids all training examples
    • It guarantees no rounding or approximation error in any representation