Интерполяция позиции для викторины по расширению контекста

Ответы и пояснения появляются по мере прохождения теста.

1. В чем основная идея позиционной интерполяции?
   • Добавьте больше внимания
   • Измените масштаб (уменьшите) индексы положения, чтобы они оставались в пределах обученного диапазона, а не экстраполировали.
   • Полностью удалить позиционные вложения
   • Переобучите модель с нуля на длинных последовательностях
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. При увеличении длины контекста с L до L' какой коэффициент масштабирования применяется базовым PI к позиции m?
   • Умножьте m на L'/L
   • Добавьте L' к м
   • Установите m на ноль
   • Разделите m на L'/L (т. е. 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