We present Position Interpolation (PI) that extends the context window sizes
of RoPE-based pretrained LLMs such as LLaMA models to up to 32768 with minimal
fine-tuning (within 1000 steps), while demonstrating strong empirical results
on various tasks that require long context, including passkey retrieval,
language modeling, and long document summarization from LLaMA 7B to 65B.
Meanwhile, the extended model by Position Interpolation preserve quality
relatively well on tasks within its original context window. To achieve this
goal, Position Interpolation linearly down-scales the input position indices to
match the original context window size, rather than extrapolating beyond the
trained context length which may lead to catastrophically high attention scores
that completely ruin the self-attention mechanism. Our theoretical study shows
that the upper bound of interpolation is at least $\sim 600 \times$ smaller
than that of extrapolation, further demonstrating its stability. Models
extended via Position Interpolation retain its original architecture and can
reuse most pre-existing optimization and infrastructure.

本文介绍了一种名为 Position Interpolation 的方法，它扩展了 RoPE-based pretrained LLMs 的上下文窗口大小，可以达到 32768，而且只需要最小限度的微调，同时在需要长上下文的各种任务中（包括密码检索、语言建模和长文档摘要等）展示了强大的实证结果。