Want to create an interactive transcript for this episode?
Podcast: Arxiv Papers
Episode: Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Description:
ModernBERT enhances BERT with optimizations, achieving state-of-the-art performance on diverse tasks while being efficient in speed and memory for GPU inference, trained on 2 trillion tokens.
https://arxiv.org/abs//2412.13663
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