bigscience-workshop/petals: 🌸 Run large language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

https://github.com/bigscience-workshop/petals

archive: https://web.archive.org/https://github.com/bigscience-workshop/petals

discussions: https://discu.eu/q/https://github.com/bigscience-workshop/petals

#bigscience #workshop #petals #run #large #language #models #at #home #bittorrent #style #fine #tuning #and #inference #up #to #10x #faster #than #offloading #github