Replicate 宣布正式支援大型語言模型（LLMs），提供快速啟動與串流 API
Original: Language models are on Replicate
Replicate, the well-known AI model hosting platform, has announced official support for large language models (LLMs) on its platform…
知名 AI 雲端託管平台 Replicate 宣布正式支援大型語言模型（LLMs）。平台已上架包括 Vicuna、Alpaca、Flan-T5 等多款開源模型，並優化了冷啟動時間。開發者現在可以透過簡單的 API 與 SDK，輕鬆在應用程式中整合語言模型的文字生成與串流（Streaming）輸出功能。
Replicate, the well-known AI model hosting platform, has announced official support for large language models (LLMs) on its platform. Previously, Replicate was primarily known for hosting image generation models such as Stable Diffusion. This update marks the formal expansion of its services into the natural language processing (NLP) domain.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Replicate Blog →Summaries are AI-generated; the original article is authoritative.