quiz bu lëkkale ak tegtal · Diggante Niveau

Kimi ak moonshot IA quiz

Xoolaat Kimi's gëna guddu contexte, Kimi K2's njaxasu-expert jëmmal, ak lu tax contexte ak model yi mëna wuute ci génne.

Yooni njiit yu jëm ciKimi ak moonshot AI
Laaj 1 de 8

What maximum context size did Moonshot announce for the moonshot-v1 API at its January 2024 public beta?

Xoolaatal laaj bu nekk8 laaj

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

  1. What maximum context size did Moonshot announce for the moonshot-v1 API at its January 2024 public beta?
    • Up to 128K tokens
    • Up to 8K tokens
    • Up to 32K tokens
    • Up to 1M tokens
  2. When does Moonshot AI’s official timeline say the company was founded?
    • Spring 2018
    • Spring 2023
    • Fall 2020
    • Winter 2025
  3. Which major investor did Alibaba disclose in its FY2024 annual report?
    • OpenAI, with an approximately 36% equity interest
    • Anthropic, with an approximately 36% equity interest
    • Moonshot AI, with an approximately 36% equity interest reported for that fiscal year
    • DeepMind, with an approximately 36% equity interest
  4. Ban architecture la model Kimi yu melni K2 di jëfandikoo ngir mëna wéy di liggéey ci anam wu yaatu?
    • Reseau yu sell yuy baaxoo
    • Garab yiy jël dogal
    • Jàppale masin vecteur
    • Njaxasu-ekspert (MoE)
  5. Lan mooy Kimi k1.5, génne ci ndoorte 2025, defar ngir gëna baaxal?
    • Jéego par jéego
    • Yokkateg nataal
    • Gaawaayu batëri
    • Rendu 3D
  6. Lan moo tax palanteer bu gudd am njariñ?
    • Dafay wàññi limu parametru model bi
    • Dafay may model bi mu xoolaat benn këyit bu gudd benn yoon
    • Dafay dindi soxla done tàggat
    • Dafay garanti dëgg gi
  7. What scale does the Kimi K2 technical report give for total and activated parameters?
    • 70 billion total, with all 70 billion activated
    • 7 billion total, with 32 billion activated
    • 1 trillion total parameters, with 32 billion activated
    • 1 trillion total, with all parameters activated for every token
  8. Why should a comparison of Kimi model capabilities identify the exact release?
    • Every release has identical capabilities
    • The product name alone establishes the model’s benchmark score
    • Version identifiers matter only for billing
    • Context limits, modalities, and tool behavior can differ across model versions