Petals - Easy way to run 100B+ language models at home
Run 100B+ language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Text-Only Accessible Website
← Home | ← All responses | View Full Version
Run 100B+ language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading