Petals: Run LLMs at home, BitTorrent-style

Petals：以BitTorrent风格在家中运行大语言模型

HN 101 分 · 31 条评论 · 作者 snorbleck · 来源 petals.dev · HN 讨论

【摘要】

The text describes a system that enables users to generate and fine-tune large language models such as Llama 3.1, Mixtral, Falcon, and BLOOM using consumer-grade GPUs or Google Colab. This is achieved through a distributed network where participants load different parts of the model to serve its various components.

⋯ 继续阅读请登录会员 ⋯