TinyLlama is a compact language model pretrained on 1 trillion tokens. It achieves better computational efficiency and outperforms existing models of similar size in downstream tasks.

https://arxiv.org/abs//2401.02385

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