RoFormer: Enhanced Transformer with Rotary Position Embedding
Encode position by rotating Q and K, so attention sees only the relative offset m−n.
Su et al. · arXiv 2021 · Foundations. Read the paper ↗
A free, interactive, animated visual explainer of RoFormer: Enhanced Transformer with Rotary Position Embedding — every exhibit computed from the real formulas, with verbatim quotes from the source.
Questions
- What is RoFormer: Enhanced Transformer with Rotary Position Embedding?
- Encode position by rotating Q and K, so attention sees only the relative offset m−n.
- Who published RoFormer: Enhanced Transformer with Rotary Position Embedding, and where?
- Su et al. — arXiv 2021 (arXiv:2104.09864).
- Where can I find a visual explainer of RoFormer: Enhanced Transformer with Rotary Position Embedding?
- Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.
Related explainers
- Attention Is All You Need
- GPT-3: Language Models are Few-Shot Learners
- Mixtral of Experts
- Training Compute-Optimal Large Language Models
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- BERT: Pre-training of Deep Bidirectional Transformers
- Scaling Laws for Neural Language Models
- Adam: A Method for Stochastic Optimization