Kvíz spojený s průvodcem · Střední úroveň
Kvantovací kvíz
Prohlédněte si hodnoty s nižší přesností, ideální hmotnost užitečného zatížení, zaokrouhlení, kalibraci GPTQ a AWQ, jádra, váhy s aktivací, afinní kódy a QAT.
Otázka 1 z 8
In a weight-focused quantization scheme, what representation property is changed?
Náhled každé otázky8 otázky
Odpovědi a vysvětlení se zobrazují, jak budete v kvízu.
- In a weight-focused quantization scheme, what representation property is changed?
- 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
- Ignoring metadata and other working memory, what fraction of raw packed-weight bits remains when moving the same weights from 16-bit to 4-bit?
- The same amount
- Twice as much
- One-hundredth in every case
- One-quarter
- Jaká je hlavní nevýhoda agresivní kvantizace?
- Chyba zaokrouhlení může snížit přesnost modelu
- Model již nelze stáhnout
- Trvale odstraní tréninková data
- Vždy to model zpomalí
- Why do the cited GPTQ and AWQ methods inspect calibration inputs?
- 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
- Why must runtime speed be measured rather than inferred from a lower weight bitwidth alone?
- 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
- 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
- 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?
- Čtyři
- Dvě
- tři
- Šest
- 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