DeepSeek V3 및 R1 추론 퀴즈

퀴즈를 풀면 정답과 설명이 나타납니다.

1. DeepSeek-V3 기술 보고서에서는 어떤 매개변수 개수를 제시했나요?
   • 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-R1의 추론 학습 및 공개에서 주목할 만한 점은 무엇인가요?
   • 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 보고서는 전체 학습 실행에 대해 어떤 연산량 수치를 제시했나요?
   • 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. 어떤 학습 신호가 DeepSeek-R1이 추론 행동을 개발하는 데 도움을 주었나요?
   • Only manually written rules with no learned model
   • Image-label classification
   • Random rewards unrelated to answers
   • Reinforcement learning rewards for correct, verifiable outcomes
5. DeepSeek-V3의 훈련과 관련된 효율성 기술 한 가지는 무엇입니까?
   • 다중 헤드 잠재 주의 및 보조 무손실 로드 밸런싱
   • 종이에 모델 인쇄하기
   • 모든 주의 레이어 제거
   • 단일 예시에 대한 교육
6. Which types of tasks did the DeepSeek-R1 paper evaluate?
   • 이미지 분류만
   • 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