🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Why do you think that https://github.com/tloen/alpaca-lora is a good alternative to petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Why do you think that https://github.com/tloen/alpaca-lora is a good alternative to petals