YaRN: Efficient Context Window Extension of Large Language Models

Extend a RoPE model to 128k by reshaping frequencies per wavelength — for a tenth of the tuning

Peng et al. · ICLR 2024 · Foundations. Read the paper ↗

A free, interactive, animated visual explainer of YaRN: Efficient Context Window Extension of Large Language Models — every exhibit computed from the real formulas, with verbatim quotes from the source.

Questions

What is YaRN: Efficient Context Window Extension of Large Language Models?
Extend a RoPE model to 128k by reshaping frequencies per wavelength — for a tenth of the tuning
Who published YaRN: Efficient Context Window Extension of Large Language Models, and where?
Peng et al. — ICLR 2024 (arXiv:2309.00071).
Where can I find a visual explainer of YaRN: Efficient Context Window Extension of Large Language Models?
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