Login
From:
Import AI
(Uncensored)
subscribe
Import AI 380: Distributed 1.3bn parameter LLM; math AI; and why reality is hard for AI | Import AI
https://jack-clark.net/2024/07/29/import-ai-380-distributed-1-3bn-parameter-llm-math-ai-and-why-reality-is-hard-for-ai/
links
backlinks
Roast topics
Find topics
Find it!
Import AI publishes first on Substack – subscribe here. Cambridge researchers show how to use distributed training to make a 1.3bn parameter LLM:…More evidence that distributed training works well …
