컨텍스트 확장 퀴즈를 위한 위치 보간

퀴즈를 풀면 정답과 설명이 나타납니다.

1. 위치 보간(Position Interpolation)의 핵심 아이디어는 무엇입니까?
   • 더 많은 관심 헤드 추가
   • 추정하는 대신 훈련된 범위 내에 머물도록 위치 인덱스의 크기를 조정(축소)합니다.
   • 위치 임베딩을 완전히 삭제
   • 긴 시퀀스에서 모델을 처음부터 다시 학습
2. Which positional scheme did the original Position Interpolation work extend through position-index rescaling?
   • A fixed output-vocabulary lookup table only
   • No positional information of any kind
   • Rotary positional embeddings, or RoPE
   • An image compression format rather than model positions
3. Why can unmodified positional extrapolation degrade a RoPE model on much longer inputs?
   • The sequence introduces positional and attention conditions beyond the model's training experience
   • A longer context automatically retrains every parameter
   • RoPE removes all attention from the model
   • The tokenizer necessarily loses its vocabulary at a specific length
4. 컨텍스트 길이를 L에서 L'로 확장하는 경우 기본 PI가 m 위치에 적용되는 재조정 요소는 무엇입니까?
   • m에 L'/L을 곱하세요
   • m에 L'을 추가하세요.
   • m을 0으로 설정
   • m을 L'/L로 나눕니다(예: m / (L'/L))
5. How does YaRN's frequency-aware approach differ from uniform Position Interpolation?
   • It removes every query and key from attention
   • It changes only the output vocabulary size
   • It treats frequency bands differently to preserve local detail while extending positional range
   • It guarantees that all long-context tasks have identical accuracy
6. What makes the original Position Interpolation workflow different from pretraining a new long-context model from scratch?
   • It eliminates every need for computation
   • It adapts an existing pretrained model toward the tested longer window with rescaling and fine-tuning
   • It requires replacing all learned parameters with random values
   • It proves all models can extend indefinitely without evaluation
7. Does basic Position Interpolation inherently add new attention heads or enlarge the trainable architecture?
   • Yes; every doubled context requires twice as many attention heads
   • Yes; the vocabulary must expand by the context-length factor
   • Only the model's filename changes, with no effect on positions
   • No; it changes the position coordinates used by the existing model
8. Why must a longer-context PI deployment still assess memory and computation requirements?
   • It processes more tokens and stores relevant state; compressing position coordinates does not remove that work
   • The number of actual input tokens shrinks automatically with their positions
   • All KV-cache storage becomes zero after rescaling
   • Every extended model has unchanged latency regardless of input length