Position Interpolation (PI) extends the context window sizes of pretrained LLMs with minimal fine-tuning, achieving strong results on tasks requiring long context while preserving quality on tasks within the original context window. PI linearly down-scales input position indices to avoid catastrophic attention scores.

https://arxiv.org/abs//2306.15595

YouTube: https://www.youtube.com/@ArxivPapers

PODCASTS:

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers