引導式測驗 · 硬 等級

DeepSeek V3 和 R1 推理測驗

測試 DeepSeek-V3 和 R1 的 MoE 架構、報告的訓練計算、RL 管道以及原始報告的精煉版本。

相關引導路徑Deepseek V3 和 R1 推理
問題 1 的 8

DeepSeek-V3 技術報告給出了哪些參數數量?

預覽每個問題8 問題

當您參加測驗時,就會出現答案和解釋。

  1. DeepSeek-V3 技術報告給出了哪些參數數量?
    • 671B total parameters, with 37B activated per token
    • 37B total parameters, all active per token
    • 671B active parameters for every token
    • A dense model with no routed experts
  2. DeepSeek-R1 的推理訓練與發布有何值得注意之處?
    • It used no training data
    • The report describes RL-based reasoning and publicly released model weights
    • It was only a closed cloud API
    • It was a rule-based program with no learned model
  3. DeepSeek-V3 報告針對其完整訓練運行給出了什麼計算數據?
    • 2.788 thousand CPU-hours
    • 2.788 million H100 GPU-hours for R1 only
    • 2.788 million H800 GPU-hours
    • No accelerator-hours were reported
  4. 什麼訓練訊號幫助 DeepSeek-R1 發展出推理行為?
    • Only manually written rules with no learned model
    • Image-label classification
    • Random rewards unrelated to answers
    • Reinforcement learning rewards for correct, verifiable outcomes
  5. 與 DeepSeek-V3 訓練相關的一種效率技術是什麼?
    • 多頭潛在註意力和輔助無損耗負載平衡
    • 將模型列印在紙上
    • 刪除所有註意力層
    • 對單一範例進行訓練
  6. Which types of tasks did the DeepSeek-R1 paper evaluate?
    • 僅影像分類
    • Mathematics, coding competitions, and STEM tasks
    • Only speech transcription
    • Only spreadsheet formatting
  7. What supervised-learning step does the DeepSeek-R1 pipeline use before its first RL stage?
    • A period of training with no text or prompts
    • A final model-compression step only
    • Cold-start supervised fine-tuning on curated reasoning examples
    • A computer-vision pretraining stage
  8. Which model families were used as bases for the released R1-distilled models?
    • BERT and CLIP
    • Tacotron and WavLM
    • NeRF and Instant-NGP
    • Qwen and Llama