Proposing an observational approach to understand language model scaling laws using 80 public models, showing predictability of model performance and emergent phenomena without extensive training across scales.

https://arxiv.org/abs//2405.10938

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

TikTok: https://www.tiktok.com/@arxiv_papers

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

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