hard20 pts · first answer countstransformerspositional-encoding
Why RoPE encodes relative position
Rotary position embeddings (RoPE) rotate query and key vectors by angles that depend on position. Why does this give relative position information?
Discussion 0
Join free to post in the discussion.
Related questions
- Scaling factor in attentionMachine Learning Engineer
- Parameters in a multi-head attention blockMachine Learning Engineer
- What LLM pretraining learnsAI Engineer (LLM & Generative AI)
- Why long contexts eat GPU memoryAI Engineer (LLM & Generative AI)
- Sizing the KV cacheAI Engineer (LLM & Generative AI)
- Why attention divides by sqrt(d_k)AI Engineer (LLM & Generative AI)
- What the causal mask preventsAI Engineer (LLM & Generative AI)