引導式測驗 · 中等 等級
上下文擴展測驗的位置插值
測試 RoPE 位置壓縮、外推、擴展因子、頻率感知方法、模型自適應和長上下文資源成本。
問題 1 的 8
位置插值的核心思想是什么?
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。
- 位置插值的核心思想是什么?
- 添加更多關注頭
- 重新調整(縮小)位置索引,使它們保持在訓練範圍內,而不是推斷
- 完全刪除位置嵌入
- 在长序列上从头开始重新训练模型
- 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
- 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
- 如果將上下文長度從 L 擴展到 L',基本 PI 將什麼重新縮放因子應用於位置 m?
- m 乘以 L'/L
- 將 L' 加到 m
- 將 m 設定為零
- m 除以 L'/L(即 m / (L'/L))
- 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
- 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
- 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
- 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