quiz bu lëkkale ak tegtal · Diggante Niveau

Laajte ci modelu arctique de neige

Natt sa xam-xam ci liggéeyu Snowflake Arctic, jëmmal MoE, njëgu tàggat biñ xamle, ak dugal ay poñ ngir saytu.

Yooni njiit yu jëm ciModèle arctique de flocon de neige
Laaj 1 de 8

Ban xeetu liggéeyukaay moo defar xeetu Arctic yi?

Xoolaatal laaj bu nekk8 laaj

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

  1. Ban xeetu liggéeyukaay moo defar xeetu Arctic yi?
    • Sosiete buy denc ay done ci cloud
    • Studio jeu video
    • Defarkatu oto
    • ab reso sosio
  2. What architecture figures did Snowflake report for Arctic?
    • A single dense network with 17B total parameters
    • 480B total parameters, with about 17B active per token
    • 480B active parameters for every token
    • A rule-based model with no neural parameters
  3. Ban liggéey moo wuutale Arctic ak chatbot yiy jëfandikoo ñépp?
    • Defar taalif ak kàdduy way
    • Fo echec
    • Liggéeyu liggéeyukaay yu melni defar SQL ak kodage
    • Soppi nataal yi
  4. Under what license did Snowflake release Arctic’s model weights?
    • Lisaas bu tëju
    • Lisaas bu abone rek
    • Amul benn lisence
    • Apache 2.0
  5. How did Snowflake characterize Arctic’s training compute budget?
    • It reported roughly under $2 million for its training compute
    • It reported a cost over one billion dollars
    • It said no computers were used
    • It did not disclose any estimate
  6. Lu ñuy jëfandikoo xeetu Arctic Embed yi?
    • Defar ay nataal
    • Seetug, seetlu, ak dooleel jëmmal-yokkum
    • Komprime wideo
    • Yorandi ay robot
  7. Which routing strategy did Snowflake report Arctic uses to choose MoE experts?
    • All-expert routing
    • Round-robin scheduling across tokens
    • Top-2 gating
    • A fixed expert selected by token position
  8. Which two types of Arctic language-model checkpoints did Snowflake release?
    • Image and audio only
    • Encoder and speech-vocoder only
    • Training and evaluation datasets only
    • Base and instruct-tuned